MCP Server
ThinkNEO Control Plane
ai.thinkneo/control-plane
What this MCP does
Provides an enterprise AI control plane for governance, guardrails, spend tracking, compliance, and model or tool routing.
Capabilities
Tools
68
tools
thinkneo_a2a_audit
Retrieve immutable audit trail for A2A interactions with hash verification. Each event is cryptographically chained for tamper detection.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_a2a_auditArguments', 'properties': {'trace_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trace Id', 'default': None, 'description': 'Filter by trace ID'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_a2a_auditOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_a2a_flow
Visualize agent-to-agent communication flow. Shows registered agents, their approval status, and interaction patterns from the live gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_a2a_flowArguments', 'properties': {'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_a2a_flowOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_a2a_log
Retrieve A2A (agent-to-agent) interaction logs from the live gateway. Shows which agents called which, actions performed, costs, and outcomes.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_a2a_logArguments', 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 50, 'description': 'Max events to return'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_a2a_logOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_a2a_policy
Retrieve A2A interaction policies from the live gateway. Shows allowed actions, rate limits, cost caps, and approval requirements.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_a2a_policyArguments', 'properties': {'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_a2a_policyOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_agent_roi
Calculate ROI per AI agent. Shows value generated vs AI cost consumed, with daily trend, success rate, and comparison to pre-AI baseline. Answers: 'Is this agent generating or consuming value?' and 'What's the ROI trend?'
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_agent_roiArguments', 'properties': {'days': {'type': 'integer', 'title': 'Days', 'default': 30, 'description': 'Number of days to analyze'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}, 'agent_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Agent Name', 'default': None, 'description': 'Specific agent to analyze. If omitted, returns all agents.'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_agent_roiOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_alert_rule_create
Create a Monitor Agent alert rule. Example: notify by email when API key 'X' reaches 75% of its budget â metric=key_spend_pct_of_budget, operator=gte, threshold=75, scope_value=<api_key_id>, budget_usd=<key budget>. Requires an admin API key.
Input schema
{'type': 'object', 'title': 'thinkneo_alert_rule_createArguments', 'required': ['name', 'metric', 'threshold'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'description': 'Human-readable rule name'}, 'metric': {'type': 'string', 'title': 'Metric', 'description': 'One of: key_spend_24h_usd, key_spend_30d_usd, key_spend_pct_of_budget, workspace_error_rate_pct, workspace_max_rps, workspace_requests, workspace_spend_24h_usd, workspace_spend_30d_usd'}, 'channels': {'type': 'string', 'title': 'Channels', 'default': 'email', 'description': 'Comma-separated: email, discord_webhook, whatsapp'}, 'operator': {'type': 'string', 'title': 'Operator', 'default': 'gte', 'description': 'Comparison: gte, gt, lte, lt, eq'}, 'severity': {'type': 'string', 'title': 'Severity', 'default': 'medium', 'description': 'low, medium, high, critical'}, 'threshold': {'type': 'number', 'title': 'Threshold', 'description': 'Threshold value to compare the metric against'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': '', 'description': "Workspace id (optional â\x80\x94 defaults to the API key's workspace)"}, 'budget_usd': {'type': 'number', 'title': 'Budget Usd', 'default': 0.0, 'description': 'Key budget in USD â\x80\x94 required for key_spend_pct_of_budget'}, 'scope_value': {'type': 'string', 'title': 'Scope Value', 'default': '', 'description': 'API key id â\x80\x94 required for key_* metrics'}, 'cooldown_minutes': {'type': 'integer', 'title': 'Cooldown Minutes', 'default': 60, 'description': 'Minimum minutes between firings'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_alert_rule_createOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_alert_rule_delete
Delete a Monitor Agent alert rule by its rule_id. Requires an admin API key.
Destructive
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_alert_rule_deleteArguments', 'required': ['rule_id'], 'properties': {'rule_id': {'type': 'string', 'title': 'Rule Id', 'description': 'The rule_id to delete (from thinkneo_alert_rule_list)'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': '', 'description': "Workspace id (optional â\x80\x94 defaults to the API key's workspace)"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_alert_rule_deleteOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_alert_rule_list
List your configurable Monitor Agent alert rules. Each rule watches a metric (e.g. an API key reaching a % of its budget, workspace spend, error rate) and notifies your channels (email/discord/whatsapp) when it fires. Requires an admin API key.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_alert_rule_listArguments', 'properties': {'workspace': {'type': 'string', 'title': 'Workspace', 'default': '', 'description': "Workspace id (optional â\x80\x94 defaults to the API key's workspace)"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_alert_rule_listOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_alert_rule_test
Send a test notification through a rule's configured channels to confirm delivery (email/discord/whatsapp). Requires an admin API key.
Input schema
{'type': 'object', 'title': 'thinkneo_alert_rule_testArguments', 'required': ['rule_id'], 'properties': {'rule_id': {'type': 'string', 'title': 'Rule Id', 'description': 'The rule_id to test (from thinkneo_alert_rule_list)'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': '', 'description': "Workspace id (optional â\x80\x94 defaults to the API key's workspace)"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_alert_rule_testOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_audit_export
Export audit events from the live gateway. Supports JSON and CSV formats with date range filtering for SIEM integration.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_audit_exportArguments', 'properties': {'format': {'type': 'string', 'title': 'Format', 'default': 'ndjson', 'description': 'Output format: ndjson or csv'}, 'end_date': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'End Date', 'default': None, 'description': 'End date ISO format'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}, 'start_date': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Start Date', 'default': None, 'description': 'Start date ISO format'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_audit_exportOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_benchmark_compare
Compare providers side-by-side for a specific task type. Shows quality scores, verification rates, and rankings based on real outcomes. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_benchmark_compareArguments', 'required': ['task_type'], 'properties': {'providers': {'anyOf': [{'type': 'array', 'items': {}}, {'type': 'null'}], 'title': 'Providers', 'default': None, 'description': "Optional list of providers to compare (e.g., ['anthropic', 'openai']). Leave empty for all."}, 'task_type': {'type': 'string', 'title': 'Task Type', 'description': "Task type to compare: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_benchmark_compareOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_benchmark_report
View the outcome benchmark matrix â real quality scores per provider/model/task_type based on verified outcomes, not static estimates. Shows verification rates, sample counts, and rankings. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_benchmark_reportArguments', 'properties': {'task_type': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Task Type', 'default': None, 'description': "Filter by task type: 'summarization', 'code_generation', 'classification', 'translation', etc. Leave empty for all."}}}
Output schema
{'type': 'object', 'title': 'thinkneo_benchmark_reportOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_bridge_a2a_to_mcp
Bridge A2A agents to MCP tool format.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_bridge_a2a_to_mcpArguments', 'properties': {'agent_name': {'type': 'string', 'title': 'Agent Name', 'default': '', 'description': 'A2A agent name to map'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_bridge_a2a_to_mcpOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_bridge_generate_agent_card
Generate an A2A Agent Card from registry data.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_bridge_generate_agent_cardArguments', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'title': 'Agent Id', 'description': 'Agent ID from registry'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_bridge_generate_agent_cardOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_bridge_list_mappings
List all MCP <-> A2A bridge mappings for a tenant.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_bridge_list_mappingsArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'thinkneo_bridge_list_mappingsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_bridge_mcp_to_a2a
Bridge MCP tool registry to A2A format. Shows tool-to-skill mappings.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_bridge_mcp_to_a2aArguments', 'properties': {'tool_name': {'type': 'string', 'title': 'Tool Name', 'default': '', 'description': 'MCP tool name to bridge'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_bridge_mcp_to_a2aOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_business_impact
Executive business impact dashboard. Returns a single view of: total value generated by AI agents, total AI cost, net ROI, risk avoided in dollars, cost per decision, top performing agents, and risk event summary. This is the report a CxO needs to justify AI investment.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_business_impactArguments', 'properties': {'period': {'type': 'string', 'title': 'Period', 'default': 'this-month', 'description': "Time period: 'this-week', 'this-month', 'this-quarter', 'all'"}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_business_impactOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_cache_status
Get semantic cache stats from the live gateway runtime metrics.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_cache_statusArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'thinkneo_cache_statusOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_check
Free-tier prompt safety check. Analyzes text for prompt injection patterns and PII (credit card numbers, Brazilian CPF, US SSN, email, phone, passwords). Returns a safety assessment with specific warnings. No authentication required.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_checkArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text', 'description': 'The text or prompt to check for safety issues (max 50,000 characters)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_checkOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_check_pii_international
Detect international PII across 30+ document types from 15+ countries: Brazil (CPF, CNPJ, RG, PIS), USA (SSN, EIN, ITIN, Passport), UK (NINO, UTR), Canada (SIN), EU (IBAN, VAT), Germany (Tax-ID), France (INSEE), Spain (DNI/NIE), Italy (Codice Fiscale), Argentina (CUIT), Mexico (CURP/RFC), Australia (TFN/ABN), India (Aadhaar/PAN), China (ID), Japan (My Number), and credit cards (Luhn validated). Required for LGPD/GDPR/HIPAA compliance. No authentication required.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_check_pii_internationalArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text', 'description': 'Text to scan for PII (max 100,000 chars)'}, 'countries': {'type': 'array', 'items': {'type': 'string'}, 'title': 'Countries', 'default': [], 'description': 'Filter by country codes (BR, US, UK, CA, EU, DE, FR, ES, IT, AR, MX, AU, IN, CN, JP, INTL). Empty = all.'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_check_pii_internationalOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_check_policy
Check AI governance policies including model access, budget limits, data controls, and agent governance from the ThinkNEO gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_check_policyArguments', 'properties': {'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace name or ID'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_check_policyOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_check_spend
Check AI spend summary for a workspace, team, or project. Returns real cost breakdown by provider, model, and time period from the ThinkNEO AI gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_check_spendArguments', 'properties': {'period': {'type': 'string', 'title': 'Period', 'default': 'this-month', 'description': 'Time period: today, this-week, this-month, last-month'}, 'group_by': {'type': 'string', 'title': 'Group By', 'default': 'provider', 'description': 'Group costs by: provider, model, team, or project'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace name or ID'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_check_spendOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_compare_models
Compare available AI models from the live gateway catalog.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_compare_modelsArguments', 'required': ['models'], 'properties': {'models': {'type': 'string', 'title': 'Models', 'description': 'Comma-separated model IDs to compare (e.g. gpt-4o,claude-sonnet-4-20250514,gemini-2.5-flash)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_compare_modelsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_complete
Run a governed LLM completion through the ThinkNEO AI gateway. The request is authorized, classified, and policy-checked against your workspace governance BEFORE any provider is called â a blocked prompt never reaches the model. Tenant/workspace are derived from your API key.
Open world
Input schema
{'type': 'object', 'title': 'thinkneo_completeArguments', 'required': ['prompt'], 'properties': {'model': {'type': 'string', 'title': 'Model', 'default': 'anthropic/claude-haiku-4-5-20251001', 'description': "provider/model, e.g. 'anthropic/claude-haiku-4-5-20251001'"}, 'prompt': {'type': 'string', 'title': 'Prompt', 'description': 'The user prompt to complete'}, 'system': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'System', 'default': None, 'description': 'Optional system instruction'}, 'max_tokens': {'type': 'integer', 'title': 'Max Tokens', 'default': 256, 'description': 'Max output tokens'}, 'temperature': {'type': 'number', 'title': 'Temperature', 'default': 0.7, 'description': 'Sampling temperature'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_completeOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_compliance_generate
Generate a compliance report for regulatory frameworks (EU AI Act, ISO 42001, SOC2, NIST). Exports from live audit data.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_compliance_generateArguments', 'properties': {'format': {'type': 'string', 'title': 'Format', 'default': 'ndjson', 'description': 'Output format: ndjson or csv'}, 'framework': {'type': 'string', 'title': 'Framework', 'default': 'eu-ai-act', 'description': 'Framework: eu-ai-act, iso-42001, soc2, nist'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_compliance_generateOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_count_tokens
Estimate token count for text (chars/4 approximation).
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_count_tokensArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text', 'description': 'Text to estimate tokens for'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_count_tokensOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_decision_cost
Analyze cost-per-decision for AI agents. Shows the actual AI cost for each decision, compared to the pre-AI baseline. Answers: 'How much does each AI decision cost?' and 'How does it compare to doing it without AI?'
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_decision_costArguments', 'properties': {'period': {'type': 'string', 'title': 'Period', 'default': 'this-month', 'description': "Time period: 'today', 'this-week', 'this-month', 'all'"}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}, 'agent_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Agent Name', 'default': None, 'description': 'Filter by specific agent'}, 'process_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Process Name', 'default': None, 'description': 'Filter by specific process'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_decision_costOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_detect_injection
Detect prompt injection attempts in text using guardrail patterns. Also retrieves live guardrails_blocked stats from the gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_detect_injectionArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text', 'description': 'Text to analyze for injection attempts'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_detect_injectionOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_detect_waste
Detect waste and inefficiency in AI operations. Analyzes agent performance, A2A communication overhead, error costs, unused capacity, and cost outliers. Returns specific actionable findings like 'you are losing $3,200/month on error retries' or 'this flow is 5x more expensive than your best-performing flow'. This is the diagnostic tool that creates the buying trigger.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_detect_wasteArguments', 'properties': {'days': {'type': 'integer', 'title': 'Days', 'default': 30, 'description': 'Analysis window in days'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_detect_wasteOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_end_trace
End an active agent trace and get the session summary. Returns total cost, duration, tool/model call counts, and event count. Triggers post-session anomaly detection (cost spikes, error rate). Requires authentication.
Input schema
{'type': 'object', 'title': 'thinkneo_end_traceArguments', 'required': ['session_id'], 'properties': {'status': {'type': 'string', 'title': 'Status', 'default': 'success', 'description': "Final session status: 'success', 'failure', or 'timeout'"}, 'session_id': {'type': 'string', 'title': 'Session Id', 'description': 'Session ID from thinkneo_start_trace'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_end_traceOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_evaluate_guardrail
Evaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_evaluate_guardrailArguments', 'required': ['text', 'workspace'], 'properties': {'text': {'type': 'string', 'title': 'Text', 'description': 'The prompt or text content to evaluate for policy violations (max 32,000 characters)'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'description': 'Workspace whose guardrail policies to apply for this evaluation'}, 'guardrail_mode': {'type': 'string', 'title': 'Guardrail Mode', 'default': 'monitor', 'description': "Evaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_evaluate_guardrailOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_evaluate_trust_score
Evaluate your organization AI Trust Score (0-100) across 10 dimensions: Guardrails, PII Protection, Injection Defense, Audit Trail, Compliance, Model Governance, Cost Controls, Outcome Validation, Observability, and Smart Routing. Returns a score, detailed breakdown, badge level (Platinum/Gold/Silver/Bronze/Unrated), and actionable recommendations. Score is valid for 30 days. Generates a public badge URL for embedding in websites and documentation. Part of the 'From Prompt to Proof' framework. Requires authentication.
Input schema
{'type': 'object', 'title': 'thinkneo_evaluate_trust_scoreArguments', 'required': ['org_name'], 'properties': {'org_name': {'type': 'string', 'title': 'Org Name', 'description': "Organization name for the trust score badge (e.g., 'Acme Corp')"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_evaluate_trust_scoreOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_budget_status
Check AI budget status including spend vs limit, forecast, and chargeback data from the ThinkNEO gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_budget_statusArguments', 'properties': {'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace name or ID'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_budget_statusOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_compliance_status
Get compliance status including framework coverage (EU AI Act, ISO 42001, NIST AI RMF, SOC 2) and governance assessments from the ThinkNEO gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_compliance_statusArguments', 'properties': {'framework': {'type': 'string', 'title': 'Framework', 'default': 'all', 'description': 'Filter by framework: eu-ai-act, iso-42001, nist-ai-rmf, soc2, all'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace name or ID'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_compliance_statusOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_observability_dashboard
Get the agent observability dashboard â aggregated metrics for your AI agents. Includes total sessions, events, cost, error rate, latency, top agents, top tools, active alerts, and cost trend over time. Like Datadog, but for AI agents. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_observability_dashboardArguments', 'properties': {'period': {'type': 'string', 'title': 'Period', 'default': '24h', 'description': "Time period: '1h', '24h', '7d', or '30d'"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_observability_dashboardOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_proof
Retrieve the immutable proof record for a verified claim. Includes the original claim, verification evidence, verifier identity, and a SHA-256 proof hash for tamper detection. This is the 'proof' in 'From Prompt to Proof'. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_proofArguments', 'required': ['claim_id'], 'properties': {'claim_id': {'type': 'string', 'title': 'Claim Id', 'description': 'UUID of the claim to get proof for'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_proofOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_savings_report
Get your AI cost savings report. Shows total requests routed, original cost (what you'd have paid with premium models), actual cost, total savings, savings percentage, breakdown by task type, and model distribution. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_savings_reportArguments', 'properties': {'period': {'type': 'string', 'title': 'Period', 'default': '30d', 'description': "Report period: '7d' (7 days), '30d' (30 days), or '90d' (90 days)"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_savings_reportOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_trace
Retrieve the full trace for an agent session. Returns the complete timeline of events (tool calls, model calls, decisions, errors), session metadata, total cost, duration, and any alerts triggered. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_traceArguments', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'title': 'Session Id', 'description': 'Session ID to retrieve the trace for'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_traceOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_get_trust_badge
Get a public AI Trust Score badge by report token. Returns the organization name, score, badge level, and validity period. Use the badge URL to embed the trust badge in websites and documentation. No authentication required.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_get_trust_badgeArguments', 'required': ['report_token'], 'properties': {'report_token': {'type': 'string', 'title': 'Report Token', 'description': 'The report token from a trust score evaluation (URL-safe string)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_get_trust_badgeOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_list_alerts
List active alerts for budget, policy, SLA, and security from the ThinkNEO gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_list_alertsArguments', 'properties': {'severity': {'type': 'string', 'title': 'Severity', 'default': 'all', 'description': 'Filter by severity: critical, high, medium, low, all'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace name or ID'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_list_alertsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_log_decision
Log a business decision made by an AI agent. Tracks the AI cost and the business value generated. If a baseline exists for the process, value is auto-calculated from the baseline cost. Example: agent 'support-bot' resolved a 'customer_support_ticket' at $0.03 AI cost, replacing a $12 human-handled ticket. ROI: 400:1.
Input schema
{'type': 'object', 'title': 'thinkneo_log_decisionArguments', 'required': ['agent_name', 'decision_type'], 'properties': {'outcome': {'type': 'string', 'title': 'Outcome', 'default': 'success', 'description': "Result: 'success', 'escalated', 'rejected', 'error'"}, 'metadata': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Metadata', 'default': None, 'description': 'JSON string with additional context'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}, 'agent_name': {'type': 'string', 'title': 'Agent Name', 'description': "Name of the AI agent that made the decision, e.g. 'support-bot', 'loan-reviewer'"}, 'confidence': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Confidence', 'default': None, 'description': 'Confidence score 0.0-1.0'}, 'ai_cost_usd': {'type': 'number', 'title': 'Ai Cost Usd', 'default': 0.0, 'description': 'Actual AI cost for this decision in USD, e.g. 0.03'}, 'process_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Process Name', 'default': None, 'description': 'Links to a baseline process for auto ROI calculation'}, 'decision_type': {'type': 'string', 'title': 'Decision Type', 'description': "Type of decision, e.g. 'ticket_resolved', 'loan_approved', 'content_reviewed'"}, 'value_generated_usd': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Value Generated Usd', 'default': None, 'description': 'Explicit business value in USD. If omitted and process_name has a baseline, auto-calculated.'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_log_decisionOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_log_event
Log an event within an active agent trace. Supports event types: tool_call, model_call, decision, error, pii_access, guardrail_triggered. Returns event_id and running session cost. Requires authentication.
Input schema
{'type': 'object', 'title': 'thinkneo_log_eventArguments', 'required': ['session_id', 'event_type'], 'properties': {'cost': {'type': 'number', 'title': 'Cost', 'default': 0.0, 'description': 'Estimated cost in USD for this event (e.g., 0.003 for an API call)'}, 'metadata': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Metadata', 'default': None, 'description': 'Optional dict with additional event context'}, 'tool_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Tool Name', 'default': None, 'description': 'Name of the tool called (for tool_call events)'}, 'event_type': {'type': 'string', 'title': 'Event Type', 'description': "Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'"}, 'latency_ms': {'type': 'integer', 'title': 'Latency Ms', 'default': 0, 'description': 'Latency in milliseconds for this event'}, 'model_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Model Name', 'default': None, 'description': "Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')"}, 'session_id': {'type': 'string', 'title': 'Session Id', 'description': 'Session ID from thinkneo_start_trace'}, 'input_summary': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Input Summary', 'default': None, 'description': 'Brief summary of the input (max 500 chars, truncated if longer)'}, 'output_summary': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Output Summary', 'default': None, 'description': 'Brief summary of the output (max 500 chars, truncated if longer)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_log_eventOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_log_risk_avoidance
Log a risk event that was blocked or avoided by the governance layer. Quantifies the estimated dollar impact of the avoided risk. Examples: PII leak blocked (est. $50K GDPR fine), prompt injection prevented, policy violation caught before production. If estimated_impact_usd is not provided, a default is calculated from severity.
Input schema
{'type': 'object', 'title': 'thinkneo_log_risk_avoidanceArguments', 'required': ['risk_type'], 'properties': {'severity': {'type': 'string', 'title': 'Severity', 'default': 'medium', 'description': "Severity level: 'low', 'medium', 'high', 'critical'"}, 'risk_type': {'type': 'string', 'title': 'Risk Type', 'description': "Type: 'pii_leak', 'injection_blocked', 'policy_violation', 'spend_limit', 'compliance_breach', 'data_exfiltration'"}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}, 'agent_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Agent Name', 'default': None, 'description': 'Agent involved, if applicable'}, 'description': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Description', 'default': None, 'description': 'Brief description of what was blocked'}, 'estimated_impact_usd': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Estimated Impact Usd', 'default': None, 'description': 'Estimated cost if this risk had materialized in USD'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_log_risk_avoidanceOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_manage_secrets
Check connector grants and secrets status from the gateway.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_manage_secretsArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'thinkneo_manage_secretsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_optimize_prompt
Analyze prompt and suggest optimizations with live metrics context.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_optimize_promptArguments', 'required': ['prompt'], 'properties': {'prompt': {'type': 'string', 'title': 'Prompt', 'description': 'Prompt text to analyze'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_optimize_promptOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_provider_status
Get real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_provider_statusArguments', 'properties': {'provider': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Provider', 'default': None, 'description': 'Specific provider to check: openai, anthropic, google, mistral, xai, cohere, or together. Omit to get status for all providers.'}, 'workspace': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Workspace', 'default': None, 'description': 'Workspace context for provider routing configuration (optional)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_provider_statusOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_read_memory
Read Claude Code project memory files. Without arguments, returns the MEMORY.md index listing all available memories. With a filename argument, returns the full content of that specific memory file. Use this to access project context, user preferences, feedback, and reference notes persisted across Claude Code sessions.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_read_memoryArguments', 'properties': {'filename': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Filename', 'default': None, 'description': "Name of the memory file to read (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Omit to get the MEMORY.md index with all available files."}}}
Output schema
{'type': 'object', 'title': 'thinkneo_read_memoryOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_register_claim
Register an action claim from an AI agent. The agent declares it performed an action (e.g., sent an email, created a PR, wrote a file) and ThinkNEO will verify it actually happened. Returns a claim_id for tracking. Part of the Outcome Validation Loop â 'From Prompt to Proof'. Requires authentication.
Input schema
{'type': 'object', 'title': 'thinkneo_register_claimArguments', 'required': ['action', 'target', 'evidence_type'], 'properties': {'action': {'type': 'string', 'title': 'Action', 'description': "Type of action claimed: 'email_sent', 'http_request', 'file_written', 'db_insert', 'pr_created', 'payment_processed', 'message_sent', 'api_call', 'task_completed', 'data_exported', 'notification_sent', 'custom'"}, 'target': {'type': 'string', 'title': 'Target', 'description': "Target of the action â\x80\x94 what was acted upon. Examples: 'user@example.com' (email), 'https://api.example.com/endpoint' (http), '/opt/data/report.pdf' (file), 'usage_log' (db table)"}, 'metadata': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Metadata', 'default': None, 'description': "Optional verification context. For http_status: {expected_status: 200, method: 'GET'}. For file_exists: {expected_hash: 'sha256...'}. For db_row_exists: {where_column: 'id', where_value: '123'}."}, 'ttl_hours': {'type': 'integer', 'title': 'Ttl Hours', 'default': 24, 'description': 'Hours until claim expires if not verified (default 24, max 168)'}, 'agent_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Agent Name', 'default': None, 'description': "Name of the agent making the claim (e.g., 'marketing-agent')"}, 'session_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session Id', 'default': None, 'description': 'Optional observability session_id to link this claim to a trace'}, 'evidence_type': {'type': 'string', 'title': 'Evidence Type', 'description': "How to verify the claim: 'http_status' (check URL response), 'file_exists' (check file path), 'db_row_exists' (check database row), 'webhook' (wait for callback), 'smtp_delivery' (check email delivery), 'manual' (flag for human review)"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_register_claimOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_registry_get
Get full details for an MCP server package from the ThinkNEO Marketplace. Returns readme, full tools list, version history, reviews, security score, and installation instructions. No authentication required.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_registry_getArguments', 'required': ['name'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'description': "Package name (e.g. 'thinkneo-control-plane', 'filesystem', 'github')"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_registry_getOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_registry_install
Get installation config for an MCP server from the ThinkNEO Marketplace. Returns ready-to-use JSON config for Claude Desktop, Cursor, Windsurf, or custom clients. Tracks the download. No authentication required.
Input schema
{'type': 'object', 'title': 'thinkneo_registry_installArguments', 'required': ['name'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'description': "Package name to install (e.g. 'thinkneo-control-plane')"}, 'client_type': {'type': 'string', 'title': 'Client Type', 'default': 'claude-desktop', 'description': 'Your MCP client: claude-desktop, cursor, windsurf, or custom'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_registry_installOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_registry_publish
Publish an MCP server to the ThinkNEO Marketplace. Validates the endpoint by calling initialize and tools/list, runs automated security scan for secrets and injection patterns, computes a security score (0-100), and stores the entry with version history. Validates the endpoint (calls initialize + tools/list), runs security scan (secrets detection, injection patterns), and stores the entry. Authentication required.
Open world
Input schema
{'type': 'object', 'title': 'thinkneo_registry_publishArguments', 'required': ['name', 'display_name', 'description', 'endpoint_url'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'description': "Package name (lowercase, hyphens allowed, e.g. 'my-mcp-server')"}, 'tags': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Tags', 'default': None, 'description': "Tags for discoverability (e.g. ['ai', 'governance', 'security'])"}, 'readme': {'type': 'string', 'title': 'Readme', 'default': '', 'description': 'Full readme/documentation in markdown'}, 'license': {'type': 'string', 'title': 'License', 'default': 'MIT', 'description': 'License (e.g. MIT, Apache-2.0)'}, 'repo_url': {'type': 'string', 'title': 'Repo Url', 'default': '', 'description': 'Source code repository URL'}, 'transport': {'type': 'string', 'title': 'Transport', 'default': 'streamable-http', 'description': 'Transport type: streamable-http, sse, or stdio'}, 'categories': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Categories', 'default': None, 'description': 'Categories: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other'}, 'description': {'type': 'string', 'title': 'Description', 'description': 'Short description of what this MCP server does (max 500 chars)'}, 'display_name': {'type': 'string', 'title': 'Display Name', 'description': 'Human-readable display name'}, 'endpoint_url': {'type': 'string', 'title': 'Endpoint Url', 'description': 'MCP server endpoint URL (e.g. https://my-server.com/mcp)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_registry_publishOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_registry_review
Rate and review an MCP server in the ThinkNEO Marketplace. One review per user per package (updates on repeat). Rating from 1 (poor) to 5 (excellent) with optional comment. Reviews affect the package average rating shown in search results. One review per user per package (updates on repeat). Authentication required.
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_registry_reviewArguments', 'required': ['name', 'rating'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'description': 'Package name to review'}, 'rating': {'type': 'integer', 'title': 'Rating', 'description': 'Rating from 1 (poor) to 5 (excellent)'}, 'comment': {'type': 'string', 'title': 'Comment', 'default': '', 'description': 'Review comment (max 2000 chars)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_registry_reviewOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_registry_search
Search the ThinkNEO MCP Marketplace â the npm for MCP tools. Discover MCP servers and tools by keyword, category, rating, or verified status. Returns name, description, tools count, rating, downloads, and verified badge. No authentication required.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_registry_searchArguments', 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 20, 'description': 'Max results to return (1-100, default 20)'}, 'query': {'type': 'string', 'title': 'Query', 'default': '', 'description': 'Search query â\x80\x94 matches name, description, tags, and tool names'}, 'category': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Category', 'default': None, 'description': 'Filter by category: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other'}, 'min_rating': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Min Rating', 'default': None, 'description': 'Minimum average rating (1.0-5.0)'}, 'verified_only': {'type': 'boolean', 'title': 'Verified Only', 'default': False, 'description': 'If true, return only verified packages'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_registry_searchOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_rotate_key
Instruct the gateway to rotate an API key.
Destructive
Input schema
{'type': 'object', 'title': 'thinkneo_rotate_keyArguments', 'required': ['key_prefix'], 'properties': {'key_prefix': {'type': 'string', 'title': 'Key Prefix', 'description': 'First 8 chars of the key to rotate'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_rotate_keyOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_route_model
AI Smart Router â find the cheapest model that meets your quality threshold. Specify your task type and quality requirements, and ThinkNEO will recommend the optimal model with estimated cost and savings vs premium models. Supports 17+ models across Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Alibaba, Cohere, and xAI. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_route_modelArguments', 'required': ['task_type'], 'properties': {'task_type': {'type': 'string', 'title': 'Task Type', 'description': 'The type of AI task: summarization, classification, code_generation, chat, analysis, translation, or embedding'}, 'text_sample': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Text Sample', 'default': None, 'description': 'Optional sample text for better routing. Helps estimate token count and task complexity. Max 500 characters.'}, 'max_latency_ms': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Max Latency Ms', 'default': None, 'description': 'Maximum acceptable latency in milliseconds. Omit for no limit.'}, 'estimated_tokens': {'type': 'integer', 'title': 'Estimated Tokens', 'default': 1000, 'description': 'Estimated total tokens for the request (input + output). Default 1000.'}, 'quality_threshold': {'type': 'integer', 'title': 'Quality Threshold', 'default': 85, 'description': 'Minimum quality score required (0-100). Default 85 = enterprise-grade.'}, 'budget_per_request': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Budget Per Request', 'default': None, 'description': 'Maximum budget per request in USD. Omit for no limit.'}, 'preferred_providers': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Preferred Providers', 'default': None, 'description': "Comma-separated list of preferred providers (e.g., 'openai,anthropic'). These will be prioritized at similar cost."}}}
Output schema
{'type': 'object', 'title': 'thinkneo_route_modelOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_router_explain
Explain why the Smart Router would choose a specific model for a task type. Shows both benchmark-based (real outcomes) and static quality estimates, and explains the reasoning behind the recommendation. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_router_explainArguments', 'required': ['task_type'], 'properties': {'task_type': {'type': 'string', 'title': 'Task Type', 'description': "Task type: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'"}, 'quality_threshold': {'type': 'integer', 'title': 'Quality Threshold', 'default': 85, 'description': 'Minimum quality score required (0-100, default 85)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_router_explainOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_schedule_demo
Schedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.
Open world
Input schema
{'type': 'object', 'title': 'thinkneo_schedule_demoArguments', 'required': ['contact_name', 'company', 'email'], 'properties': {'role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Role', 'default': None, 'description': "Contact's role: cto, cfo, security, engineering, or other"}, 'email': {'type': 'string', 'title': 'Email', 'description': 'Business email address to receive follow-up from the ThinkNEO team'}, 'company': {'type': 'string', 'title': 'Company', 'description': 'Company or organization name'}, 'context': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Context', 'default': None, 'description': 'Additional context such as current AI providers used, request volume, or specific use case'}, 'interest': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Interest', 'default': None, 'description': 'Primary area of interest: guardrails, finops, observability, governance, or full platform'}, 'contact_name': {'type': 'string', 'title': 'Contact Name', 'description': 'Full name of the person requesting the demo'}, 'preferred_dates': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Preferred Dates', 'default': None, 'description': "Preferred meeting dates, times, and timezone (e.g., 'Tuesdays or Thursdays, 9-11am EST')"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_schedule_demoOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_set_baseline
Define the pre-AI cost baseline for a business process. Example: 'customer_support_ticket costs $12 per ticket and takes 15 minutes without AI'. This baseline is used to calculate ROI when agents handle the same process. Call this once per process to establish the comparison point.
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_set_baselineArguments', 'required': ['process_name', 'cost_per_unit_usd'], 'properties': {'notes': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Notes', 'default': None, 'description': 'Additional context about this baseline'}, 'workspace': {'type': 'string', 'title': 'Workspace', 'default': 'default', 'description': 'Workspace identifier'}, 'unit_label': {'type': 'string', 'title': 'Unit Label', 'default': 'unit', 'description': "What one unit represents, e.g. 'ticket', 'review', 'decision', 'document'"}, 'process_name': {'type': 'string', 'title': 'Process Name', 'description': "Name of the business process, e.g. 'customer_support_ticket', 'loan_review', 'content_moderation'"}, 'cost_per_unit_usd': {'type': 'number', 'title': 'Cost Per Unit Usd', 'description': 'Pre-AI cost per unit in USD, e.g. 12.00 for a $12 support ticket'}, 'avg_duration_minutes': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Avg Duration Minutes', 'default': None, 'description': 'Average time in minutes for one unit without AI, e.g. 15'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_set_baselineOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_simulate_savings
Simulate how much your organization would save on AI costs using ThinkNEO Smart Router. Enter your current monthly AI spend and primary model, and see estimated monthly and annual savings with a recommended model mix. No authentication required â try it now!
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_simulate_savingsArguments', 'required': ['monthly_ai_spend'], 'properties': {'primary_model': {'type': 'string', 'title': 'Primary Model', 'default': 'gpt-4o', 'description': "Your primary model: 'gpt-4o', 'claude-opus-4', 'claude-sonnet-4', 'gpt-4.1', or 'gemini-2.5-pro'"}, 'monthly_ai_spend': {'type': 'number', 'title': 'Monthly Ai Spend', 'description': 'Your current monthly AI API spend in USD (e.g., 5000.00)'}, 'task_distribution': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Task Distribution', 'default': None, 'description': 'JSON string of task distribution, e.g., \'{"chat": 0.3, "summarization": 0.2, "code_generation": 0.2, "classification": 0.15, "analysis": 0.1, "translation": 0.05}\'. Values should sum to ~1.0. Omit for default enterprise distribution.'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_simulate_savingsOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_sla_breaches
View SLA breach history â which SLAs were breached, by which agents, actual vs threshold values, and resolution status. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_sla_breachesArguments', 'properties': {'days': {'type': 'integer', 'title': 'Days', 'default': 30, 'description': 'Days to look back (default 30)'}, 'agent_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Agent Name', 'default': None, 'description': 'Filter by agent name'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_sla_breachesOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_sla_dashboard
SLA overview dashboard â all agents, current status, error budgets, and recent breaches (7d). The SRE dashboard for AI agents. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_sla_dashboardArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'thinkneo_sla_dashboardOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_sla_define
Define or update an SLA (Service Level Agreement) for an AI agent. Set accuracy, quality, cost, safety, or latency thresholds with automatic breach detection and configurable actions (alert, escalate, disable, switch_model). Like SRE SLOs but for AI agent outcomes. Requires authentication.
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_sla_defineArguments', 'required': ['agent_name', 'metric', 'threshold'], 'properties': {'metric': {'type': 'string', 'title': 'Metric', 'description': "Metric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)"}, 'window': {'type': 'string', 'title': 'Window', 'default': '7d', 'description': "Rolling window: '1h', '24h', '7d', or '30d'"}, 'threshold': {'type': 'number', 'title': 'Threshold', 'description': 'Target threshold value (e.g., 95.0 for 95% accuracy)'}, 'agent_name': {'type': 'string', 'title': 'Agent Name', 'description': "Agent name to set SLA for (e.g., 'support-bot', 'finance-agent')"}, 'breach_action': {'type': 'string', 'title': 'Breach Action', 'default': 'alert', 'description': "Action on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)"}, 'threshold_direction': {'type': 'string', 'title': 'Threshold Direction', 'default': 'min', 'description': "'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency)."}}}
Output schema
{'type': 'object', 'title': 'thinkneo_sla_defineOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_sla_status
Check current SLA status for all agents or a specific agent. Shows actual metric values vs thresholds, healthy/breached status, and error budget remaining. Automatically records breaches. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_sla_statusArguments', 'properties': {'agent_name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Agent Name', 'default': None, 'description': 'Optional: specific agent name. Leave empty for all agents.'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_sla_statusOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_start_trace
Start a new agent observability trace. Creates a session that tracks all tool calls, model calls, decisions, and errors for an AI agent run. Returns a session_id to use with thinkneo_log_event and thinkneo_end_trace. Requires authentication.
Input schema
{'type': 'object', 'title': 'thinkneo_start_traceArguments', 'required': ['agent_name'], 'properties': {'metadata': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'title': 'Metadata', 'default': None, 'description': 'Optional dict with additional context (e.g., {"task": "email-draft", "user_id": "u123"})'}, 'agent_name': {'type': 'string', 'title': 'Agent Name', 'description': "Name of the agent being traced (e.g., 'marketing-agent', 'support-bot')"}, 'agent_type': {'type': 'string', 'title': 'Agent Type', 'default': 'generic', 'description': "Type of agent: 'assistant', 'autonomous', 'workflow', 'pipeline', or 'generic'"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_start_traceOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_usage
Returns usage statistics for your ThinkNEO API key. Shows calls today, this week, this month, monthly limit, remaining calls, top tools used, estimated cost, and current tier. Works without authentication (returns general info).
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_usageArguments', 'properties': {}}
Output schema
{'type': 'object', 'title': 'thinkneo_usageOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_verification_dashboard
Aggregated outcome verification metrics â verification rates, failure patterns, agent reliability rankings, and daily trends. Shows how reliably your AI agents are delivering verified outcomes. 'Datadog for AI outcomes'. Requires authentication.
Read only
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_verification_dashboardArguments', 'properties': {'period': {'type': 'string', 'title': 'Period', 'default': '7d', 'description': "Time period: '24h', '7d', or '30d'"}}}
Output schema
{'type': 'object', 'title': 'thinkneo_verification_dashboardOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_verify_claim
Trigger verification of a registered action claim. Runs the appropriate verification adapter (HTTP check, file check, database check, etc.) and returns the result with evidence. If already verified, returns cached result (use force=true to re-verify). Part of the Outcome Validation Loop â 'From Prompt to Proof'. Requires authentication.
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_verify_claimArguments', 'required': ['claim_id'], 'properties': {'force': {'type': 'boolean', 'title': 'Force', 'default': False, 'description': 'Force re-verification even if already verified/failed'}, 'claim_id': {'type': 'string', 'title': 'Claim Id', 'description': 'UUID of the claim to verify (from thinkneo_register_claim)'}}}
Output schema
{'type': 'object', 'title': 'thinkneo_verify_claimOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
thinkneo_write_memory
Write or update a Claude Code project memory file (.md). Persists project context, user preferences, feedback, and reference notes across Claude Code sessions. Filename must end in .md with lowercase alphanumeric characters. Path traversal is blocked. Requires authentication.Use this to persist project context, user preferences, feedback, and reference notes across Claude Code sessions. The filename must end in .md and contain only lowercase letters, digits, underscores, and hyphens (e.g. 'user_fabio.md', 'project_new_feature.md'). Path traversal is blocked.
Idempotent
Input schema
{'type': 'object', 'title': 'thinkneo_write_memoryArguments', 'required': ['filename', 'content'], 'properties': {'content': {'type': 'string', 'title': 'Content', 'description': 'Full markdown content to write to the file.'}, 'filename': {'type': 'string', 'title': 'Filename', 'description': "Name of the memory file to write (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Must end in .md."}}}
Output schema
{'type': 'object', 'title': 'thinkneo_write_memoryOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
History
Recent tool changes
Added
thinkneo_alert_rule_test
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_alert_rule_delete
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_alert_rule_create
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_alert_rule_list
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_check_pii_international
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_detect_injection
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_cache_status
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_manage_secrets
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_rotate_key
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_optimize_prompt
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_count_tokens
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_compare_models
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_audit_export
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_sla_dashboard
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_sla_breaches
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_sla_status
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_sla_define
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_compliance_generate
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_router_explain
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_benchmark_compare
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_benchmark_report
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_verification_dashboard
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_get_proof
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_verify_claim
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_register_claim
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_detect_waste
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_a2a_audit
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_a2a_flow
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_a2a_policy
Sept. 17, 2026, 7:57 a.m.
Added
thinkneo_a2a_log
Sept. 17, 2026, 7:57 a.m.
Discover
Similar MCP servers
FLOCORE Governed MCP
tech.flocore/flocore
Provides governed tenant-scoped operational queries, ticket and queue management, provenance-backed memory, and prompt-injection …
GAIP — evidence on AI agents before and after you call them
io.github.tjcgraham-rgb/gaip-broker
Assesses agent and service metadata, prepares delegation evidence, verifies receipts and task results, checks governance boundari…
AIMEAT
io.aimeat/aimeat
Provides a self-hosted agent operating system with agent work delegation, access controls, federation, hooks, SSO, security admin…
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
Proof Holdings
holdings.proof/mcp-server
Provides domain verification, identity and delegation proofs, human approval workflows, trusted-contact challenges, and controlle…
GoCreative Agent API
io.github.ColinHughes2121/gocreative-agent-api
Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…
Japan Public Ledgers MCP
com.mcp-revenue-empire/japan-public-ledgers
Provides agent identity, memory, audit, trust, proxy, temporary email, webhook, CAPTCHA, and alerting capabilities alongside publ…
PHION Agent Trust Infrastructure
systems.phion/evidence-engine
Provides agent trust, policy, provenance, evidence, delegation, telemetry, and transaction-control services for MCP and agent wor…