此 MCP 可以做什么
Provides agent infrastructure for deduplication, cost prediction, validation, governance, and failure analysis.
工具
输入模式
{'type': 'object', 'properties': {'daily_limit': {'type': 'number', 'description': 'Optional. Daily budget in USD (e.g., 10.0 for a $10/day cap). Enables budget alerts and remaining-balance calculation.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'date': {'type': 'string'}, 'spend': {'type': 'object', 'properties': {'by_model': {'type': 'array', 'items': {'type': 'object'}}, 'total_usd': {'type': 'number'}, 'total_calls': {'type': 'number'}, 'total_usd_formatted': {'type': 'string'}}}, 'alerts': {'type': 'array', 'items': {'type': 'string'}}, 'projection': {'type': 'object', 'properties': {'hourly_rate_usd': {'type': 'number'}, 'hours_remaining': {'type': 'number'}, 'projected_day_total_usd': {'type': 'number'}}}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['plan'], 'properties': {'plan': {'type': 'array', 'items': {'type': 'object', 'required': ['step', 'provider', 'model', 'estimated_input_tokens', 'estimated_output_tokens'], 'properties': {'step': {'type': 'string', 'description': 'Step identifier — string label or number.'}, 'model': {'type': 'string', 'description': 'Model name: claude-sonnet-4-6, gpt-4o, etc.'}, 'provider': {'type': 'string', 'description': 'LLM provider: anthropic, openai, google, etc.'}, 'search_calls': {'type': 'number', 'description': 'Optional. Number of grounding/search calls (e.g. Gemini Search).'}, 'cache_read_tokens': {'type': 'number', 'description': 'Optional. Cached prompt tokens for providers with prompt caching.'}, 'estimated_input_tokens': {'type': 'number', 'description': 'Estimated prompt token count.'}, 'estimated_output_tokens': {'type': 'number', 'description': 'Estimated completion token count.'}}}, 'description': 'Array of plan steps with provider, model, and token estimates.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'estimate': {'type': 'object', 'properties': {'steps': {'type': 'array', 'items': {'type': 'object'}}, 'step_count': {'type': 'number'}, 'pricing_as_of': {'type': 'string'}, 'pricing_source': {'type': 'string'}, 'total_cost_usd': {'type': 'number'}, 'estimate_complete': {'type': 'boolean'}, 'unrecognized_models': {'type': 'array', 'items': {'type': 'string'}}, 'recognized_step_count': {'type': 'number'}, 'total_cost_usd_formatted': {'type': 'string'}}}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}, 'optimization_suggestions': {'type': 'array', 'items': {'type': 'string'}}}}
输入模式
{'type': 'object', 'required': ['plan'], 'properties': {'plan': {'type': 'array', 'items': {'type': 'object', 'required': ['step', 'provider', 'model', 'estimated_input_tokens', 'estimated_output_tokens'], 'properties': {'step': {'type': 'string', 'description': 'Step identifier — string label or number.'}, 'model': {'type': 'string', 'description': 'Model name.'}, 'provider': {'type': 'string', 'description': 'LLM provider.'}, 'estimated_input_tokens': {'type': 'number', 'description': 'Estimated input tokens.'}, 'estimated_output_tokens': {'type': 'number', 'description': 'Estimated output tokens.'}}}, 'description': 'Array of plan steps. Same schema as burnrate_estimate: each step needs step, provider, model, estimated_input_tokens, estimated_output_tokens.'}, 'target_budget': {'type': 'number', 'description': 'Optional. Target total cost in USD.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'steps': {'type': 'array', 'items': {'type': 'object'}}, 'original': {'type': 'object', 'properties': {'total_cost_usd': {'type': 'number'}, 'total_cost_usd_formatted': {'type': 'string'}}}, 'optimized': {'type': 'object', 'properties': {'total_cost_usd': {'type': 'number'}, 'total_savings_pct': {'type': 'number'}, 'total_savings_usd': {'type': 'number'}, 'total_cost_usd_formatted': {'type': 'string'}}}, 'request_id': {'type': 'string'}, 'suggestions': {'type': 'array', 'items': {'type': 'string'}}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['provider', 'model', 'input_tokens', 'output_tokens'], 'properties': {'model': {'type': 'string', 'description': 'Model identifier as returned by the provider. Examples: claude-sonnet-4-6, gpt-4o, gemini-2.0-flash, mistral-large-latest. Unknown models are accepted but cost may show as $0.'}, 'task_id': {'type': 'string', 'description': 'Optional task ID for cross-referencing spend with DedupQ deduplication results. Use the same task_id passed to dedupq_check to link cost tracking with deduplication.'}, 'provider': {'type': 'string', 'description': 'LLM provider identifier. Supported: anthropic, openai, google, mistral, cohere, deepseek, together, fireworks, groq. Must match the provider of the model used.'}, 'input_tokens': {'type': 'number', 'description': 'Actual prompt tokens used. Must be >= 0.'}, 'output_tokens': {'type': 'number', 'description': 'Actual completion tokens used. Must be >= 0.'}, 'cache_read_tokens': {'type': 'number', 'description': 'Optional. Cache-read tokens.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'model': {'type': 'string'}, 'tracked': {'type': 'boolean'}, 'provider': {'type': 'string'}, 'record_id': {'type': 'string'}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'input_tokens': {'type': 'number'}, 'output_tokens': {'type': 'number'}, 'pricing_found': {'type': 'boolean'}, 'actual_cost_usd': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}, 'actual_cost_usd_formatted': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['content'], 'properties': {'content': {'type': 'string', 'description': 'The task content to check for duplicates. This is hashed and embedded for matching.'}, 'task_id': {'type': 'string', 'description': 'Optional caller task ID for tracing and cross-referencing with BurnRate.'}, 'hash_only': {'type': 'boolean', 'description': 'If true, skip vector similarity search and use exact hash matching only. Default: false.'}, 'similarity_threshold': {'type': 'number', 'description': 'Cosine similarity threshold for semantic matching, 0.0 to 1.0. Default: 0.80.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'match': {'type': 'object', 'properties': {'task_id': {'type': 'string'}, 'cached_at': {'type': 'string'}, 'match_type': {'type': 'string'}, 'similarity': {'type': 'number'}}}, 'status': {'type': 'string', 'description': 'hit | miss | in_progress'}, 'cache_hit': {'type': 'string'}, 'request_id': {'type': 'string'}, 'content_hash': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'cache_age_seconds': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['content', 'result'], 'properties': {'result': {'description': 'The task result to cache. Can be any JSON value.'}, 'content': {'type': 'string', 'description': 'Original task content. Used to compute hash and embedding for future matching.'}, 'task_id': {'type': 'string', 'description': 'Optional task ID. Used as the database row ID if provided.'}, 'hash_only': {'type': 'boolean', 'description': 'If true, skip embedding generation. Default: false.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'stored': {'type': 'boolean'}, 'task_id': {'type': 'string'}, 'request_id': {'type': 'string'}, 'content_hash': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'has_embedding': {'type': 'boolean'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['agent_id', 'proposed_action'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent identifier.'}, 'proposed_action': {'type': 'object', 'required': ['type'], 'properties': {'type': {'type': 'string', 'description': 'Action type: http_request, delete_file, send_email, etc.'}}, 'description': 'Action to evaluate. Must contain a \'type\' field. Example: {"type": "http_request", "url": "https://external.example.com"} or {"type": "file_write", "path": "/etc/config"}.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'reason': {'type': 'string'}, 'audit_id': {'type': 'string'}, 'decision': {'enum': ['allow', 'deny', 'stub'], 'type': 'string'}, 'policy_id': {'type': 'string'}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['name', 'rules'], 'properties': {'name': {'type': 'string', 'description': "Unique policy name per org. Examples: 'no-delete-in-prod', 'budget-cap-50', 'pii-block'."}, 'rules': {'type': 'array', 'items': {'type': 'object', 'required': ['operator'], 'properties': {'field': {'type': 'string', 'description': "Field path on proposed_action (e.g. 'action_type', 'path', 'amount')."}, 'rules': {'type': 'array', 'description': 'Nested rules for compound operators (and/or/not).'}, 'value': {'type': 'string', 'description': 'Comparison value for leaf operators. String, number, or boolean as string.'}, 'operator': {'type': 'string', 'description': 'Rule operator: eq | starts_with | contains | gt | lt | and | or | not.'}}}, 'description': "Array of rule objects evaluated against the proposed_action in guardrail_check. Leaf operators: eq, starts_with, contains, gt, lt (compare field to value). Compound operators: and, or, not (nest sub-rules in a rules array). Example: [{operator:'eq', field:'type', value:'file_write'}] blocks all file writes. Nested example: [{operator:'and', rules:[{operator:'eq',field:'type',value:'api_call'},{operator:'contains',field:'url',value:'prod'}]}] blocks prod API calls."}, 'priority': {'type': 'number', 'description': 'Optional. Evaluation order. Default: 0.'}, 'description': {'type': 'string', 'description': 'Optional human-readable summary of what this policy enforces. Returned in guardrail_check responses and guardrail_list_policies output for auditability.'}, 'action_types': {'type': 'array', 'items': {'type': 'string'}, 'description': "Optional. Restrict this policy to only evaluate when proposed_action.type matches one of these values. Examples: ['file_write', 'api_call', 'db_delete']. Omit to apply the policy to all action types regardless of type field."}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'policy': {'type': 'object', 'properties': {'id': {'type': 'string'}, 'name': {'type': 'string'}, 'rules': {'type': 'array'}, 'enabled': {'type': 'boolean'}, 'priority': {'type': 'number'}, 'created_at': {'type': 'string'}, 'description': {'type': 'string'}, 'action_types': {'type': 'array', 'items': {'type': 'string'}}}}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['task_type'], 'properties': {'filters': {'type': 'object', 'properties': {'language': {'type': 'string', 'description': 'Programming language.'}, 'provider': {'type': 'string', 'description': 'LLM provider.'}, 'framework': {'type': 'string', 'description': 'Framework.'}}, 'description': 'Optional filters.'}, 'task_type': {'type': 'string', 'description': 'Task category: code_generation, web_search, data_analysis, etc.'}, 'task_description': {'type': 'string', 'description': 'Optional. Natural-language task description for semantic search.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'pitfalls': {'type': 'array', 'items': {'type': 'object', 'properties': {'id': {'type': 'string'}, 'fix': {'type': 'string'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'reports': {'type': 'number'}, 'severity': {'type': 'string'}, 'frequency': {'type': 'string'}, 'description': {'type': 'string'}, 'fix_confidence': {'type': 'number'}}}}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'total_matching': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['task_type', 'task_description', 'failure'], 'properties': {'failure': {'type': 'object', 'properties': {'language': {'type': 'string', 'description': 'Programming language.'}, 'provider': {'type': 'string', 'description': 'LLM provider.'}, 'framework': {'type': 'string', 'description': 'Framework.'}, 'error_type': {'type': 'string', 'description': 'Error category: tool_call_ignored, syntax_error, etc.'}, 'fix_worked': {'type': 'boolean', 'description': 'Whether the fix worked.'}, 'root_cause': {'type': 'string', 'description': 'Root cause analysis (PII-scrubbed).'}, 'fix_applied': {'type': 'string', 'description': 'Fix applied (PII-scrubbed).'}, 'error_message': {'type': 'string', 'description': 'Error message (PII-scrubbed).'}}, 'description': 'Failure details.'}, 'task_type': {'type': 'string', 'description': 'Task category.'}, 'task_description': {'type': 'string', 'description': 'Description of the failed task.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'message': {'type': 'string'}, 'verified': {'type': 'boolean'}, 'report_id': {'type': 'string'}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}, 'linked_pitfall_id': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['output'], 'properties': {'output': {'type': 'string', 'description': 'The agent output text to validate.'}, 'schema': {'type': 'object', 'description': 'JSON Schema to validate output against.'}, 'language': {'type': 'string', 'description': 'Code language for syntax check: json, python, javascript, typescript.'}, 'override': {'type': 'boolean', 'description': 'Force pass. Requires override_reason.'}, 'directives': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'value'], 'properties': {'name': {'type': 'string', 'description': 'Optional directive name.'}, 'type': {'type': 'string', 'description': 'Directive type.'}, 'value': {'type': 'string', 'description': 'Directive value — string pattern, regex, keyword array (as comma-separated string), or number (as string). Interpreted based on directive type.'}}}, 'description': 'Directive objects. Types: must_include, must_not_include, must_match, must_not_match, must_contain, must_not_contain, min_length, max_length.'}, 'check_types': {'type': 'array', 'items': {'enum': ['directive_compliance', 'schema_validation', 'code_syntax', 'tone', 'factual_claims'], 'type': 'string'}, 'description': 'Checks to run. Auto-inferred if omitted.'}, 'override_reason': {'type': 'string', 'description': 'Required when override is true.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'issues': {'type': 'array', 'items': {'type': 'object', 'properties': {'type': {'type': 'string'}, 'message': {'type': 'string'}, 'severity': {'type': 'string'}}}}, 'summary': {'type': 'object', 'properties': {'total': {'type': 'number'}, 'errors': {'type': 'number'}, 'warnings': {'type': 'number'}}}, 'verdict': {'enum': ['pass', 'warn', 'fail'], 'type': 'string'}, 'checks_run': {'type': 'array', 'items': {'type': 'string'}}, 'request_id': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'credits_remaining': {'type': 'number'}, 'fallback_behavior': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['task_description'], 'properties': {'context': {'type': 'object', 'properties': {'additional_context': {'type': 'string', 'description': 'Free-form context the workflow steps can reference.'}}, 'description': 'Additional context for the workflow.'}, 'delivery': {'type': 'object', 'properties': {'method': {'type': 'string', 'description': 'sse | webhook | polling. Default for MCP: polling.'}, 'webhook_url': {'type': 'string', 'description': 'Required if method is webhook. Must be HTTPS.'}}, 'description': "Delivery method. Default: polling (MCP clients typically can't handle SSE)."}, 'task_type': {'type': 'string', 'description': "Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, compose, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. Call GET /api/rigor/task-types for the full vocabulary with each type's shape."}, 'preferences': {'type': 'object', 'properties': {'execution': {'enum': ['direct'], 'type': 'string', 'description': "Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Falls back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. Attachments and prior_workflow_id chaining are NOT applied — use standard execution for those."}, 'rigor_level': {'type': 'string', 'description': 'quick | standard (default) | thorough. Controls analysis depth and cost.'}, 'max_budget_usd': {'type': 'number', 'description': 'Maximum budget in USD.'}, 'output_contract': {'type': 'object', 'required': ['task_type', 'shape', 'fields'], 'properties': {'count': {'type': 'object', 'properties': {'max': {'type': 'number'}, 'min': {'type': 'number'}}, 'description': 'Bounds on the number of entries. Only read when shape is "array".'}, 'shape': {'enum': ['object', 'array'], 'type': 'string', 'description': '"object" for 1 record, "array" for 1 entry per input item.'}, 'fields': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'type'], 'properties': {'enum': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Restricts a string field to a fixed set of values.'}, 'name': {'type': 'string', 'description': 'The JSON key.'}, 'type': {'enum': ['string', 'number', 'integer', 'boolean', 'array', 'object'], 'type': 'string', 'description': "The value's type."}, 'maximum': {'type': 'number', 'description': 'Upper bound for a numeric field.'}, 'minimum': {'type': 'number', 'description': 'Lower bound for a numeric field.'}, 'required': {'type': 'boolean', 'description': 'Defaults to true. Set false for a field that may be absent.'}, 'description': {'type': 'string', 'description': "Passed to the model as the field's description."}}}, 'description': 'The schema for 1 record.'}, 'selection': {'type': 'object', 'properties': {'maxCount': {'type': 'number'}, 'minCount': {'type': 'number'}, 'minScore': {'type': 'number'}, 'scoreField': {'type': 'string'}}, 'description': 'Use when you want the model to over-generate candidates and Rigor to sort, threshold, and cap them before the count bounds are checked.'}, 'task_type': {'type': 'string', 'description': 'Your own label for the work. Echoed into telemetry. Not read as a framework name and does not change routing.'}}, 'description': 'Only read when execution is "direct". Declares the JSON shape you want back, so the answer is generated against your schema and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key.'}}, 'description': 'Optional workflow preferences.'}, 'task_description': {'type': 'string', 'description': "Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'"}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'ok': {'type': 'boolean'}, 'status': {'type': 'string'}, 'poll_url': {'type': 'string'}, 'execution': {'type': 'string', 'description': "Present with value 'direct' when direct execution ran. Absent for standard multi-call execution."}, 'task_type': {'type': 'string'}, 'value_class': {'type': 'string'}, 'workflow_id': {'type': 'string'}, 'delivery_mode': {'type': 'string'}, 'available_modes': {'type': 'array', 'items': {'type': 'string'}}, 'estimated_credits': {'type': 'number'}, 'execution_fallback': {'type': 'boolean', 'description': 'True when you explicitly requested direct execution and it could not be honoured — the workflow ran as standard multi-call instead. Never set for an auto-selected attempt, since you did not ask.'}}}
输入模式
{'type': 'object', 'required': ['task_description'], 'properties': {'task_type': {'type': 'string', 'description': "Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types: solution_design, requirements_analysis, code_implementation, code_review, bug_fix, root_cause_analysis, incident_response, deployment_execution, competitive_scan, financial_analysis, research_task, documentation, governance_change, compliance_audit, data_security_assessment, performance_optimization, user_story_definition, implementation_prompt_generation. Atomic single-call types, which auto-select direct execution: tag, score, rerank, compose, extract_entities, parse_query, quick_research, quick_classification, quick_extraction, quick_scoring. Call GET /api/rigor/task-types for the full vocabulary with each type's shape."}, 'preferences': {'type': 'object', 'properties': {'execution': {'enum': ['direct'], 'type': 'string', 'description': "Set to 'direct' to compose the plan's content frameworks into a single LLM call and route cost-first, using a per-task-type model floor that moves when a cheaper model earns the work. Research steps, process steps (classification-verify, review protocol, synthesis) and the quality review each remain separate calls, so this is not a one-call-per-workflow guarantee: for atomic task types, which have a single content framework, the call count matches standard execution and the saving is the model. Supplying output_contract replaces the quality-review call with deterministic validation, which is one fewer call. No intermediate outputs. Available at every tier. Auto-selected for atomic task types when no execution preference is given. Falls back to standard execution when combined with require_approval or interactive mode, or when the plan exceeds the composition size limit. Attachments and prior_workflow_id chaining are NOT applied — use standard execution for those."}, 'rigor_level': {'enum': ['quick', 'standard', 'thorough'], 'type': 'string', 'description': 'Review depth. Default auto-detected from task complexity.'}, 'add_frameworks': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Inject additional frameworks into the plan.'}, 'max_budget_usd': {'type': 'number', 'description': 'Budget ceiling in USD. Triggers warning if plan exceeds this.'}, 'only_frameworks': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Restrict plan to only these frameworks (mutex with skip_frameworks).'}, 'output_contract': {'type': 'object', 'required': ['task_type', 'shape', 'fields'], 'properties': {'count': {'type': 'object', 'properties': {'max': {'type': 'number'}, 'min': {'type': 'number'}}, 'description': 'Bounds on the number of entries. Only read when shape is "array".'}, 'shape': {'enum': ['object', 'array'], 'type': 'string', 'description': '"object" for 1 record, "array" for 1 entry per input item.'}, 'fields': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'type'], 'properties': {'enum': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Restricts a string field to a fixed set of values.'}, 'name': {'type': 'string', 'description': 'The JSON key.'}, 'type': {'enum': ['string', 'number', 'integer', 'boolean', 'array', 'object'], 'type': 'string', 'description': "The value's type."}, 'maximum': {'type': 'number', 'description': 'Upper bound for a numeric field.'}, 'minimum': {'type': 'number', 'description': 'Lower bound for a numeric field.'}, 'required': {'type': 'boolean', 'description': 'Defaults to true. Set false for a field that may be absent.'}, 'description': {'type': 'string', 'description': "Passed to the model as the field's description."}}}, 'description': 'The schema for 1 record.'}, 'selection': {'type': 'object', 'properties': {'maxCount': {'type': 'number'}, 'minCount': {'type': 'number'}, 'minScore': {'type': 'number'}, 'scoreField': {'type': 'string'}}, 'description': 'Use when you want the model to over-generate candidates and Rigor to sort, threshold, and cap them before the count bounds are checked.'}, 'task_type': {'type': 'string', 'description': 'Your own label for the work. Echoed into telemetry. Not read as a framework name and does not change routing.'}}, 'description': 'Only read when execution is "direct". Declares the JSON shape you want back, so the answer is generated against your schema and validated against it before return, instead of returned as prose you have to parse. A conforming run also skips the quality-review call, costing 1 LLM call rather than 2. The schema is closed: a record carrying an undeclared key is rejected exactly like one missing a required key.'}, 'skip_frameworks': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Framework names to exclude from the plan.'}, 'require_approval': {'type': 'boolean', 'description': 'Pause at pending_approval before the final step.'}, 'approval_before_step': {'type': 'array', 'items': {'type': 'number'}, 'description': 'Zero-based step indices where approval gates are inserted.'}}, 'description': 'Optional workflow preferences.'}, 'task_description': {'type': 'string', 'description': "Natural language description of the task. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Redis integration.'"}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'ok': {'type': 'boolean'}, 'plan': {'type': 'object', 'properties': {'cost': {'type': 'object', 'properties': {'usd': {'type': 'number'}, 'range': {'type': 'object'}, 'credits': {'type': 'number'}}}, 'info': {'type': 'array', 'items': {'type': 'string'}}, 'sequence': {'type': 'array', 'items': {'type': 'object', 'properties': {'name': {'type': 'string'}, 'step': {'type': 'number'}, 'estimated_credits': {'type': 'number'}}}}, 'warnings': {'type': 'array', 'items': {'type': 'object', 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}, 'suggestion': {'type': 'string'}}}}, 'rigor_level': {'type': 'string'}, 'workflow_id': {'type': 'string'}, 'alternatives': {'type': 'object'}, 'allowed_modes': {'type': 'array', 'items': {'type': 'string'}, 'description': "Execution modes available for this plan beyond the standard multi-call default. Contains 'direct' when the plan is eligible for direct execution; empty array when it is not."}, 'classification': {'type': 'object', 'properties': {'task_type': {'type': 'string'}, 'value_class': {'type': 'string'}}}}}, 'generated_title': {'type': 'string'}}}
输入模式
{'type': 'object', 'required': ['workflow_id'], 'properties': {'workflow_id': {'type': 'string', 'description': 'The workflow ID returned by rigor_execute (format: wr_xxx).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'ok': {'type': 'boolean'}, 'workflow': {'type': 'object', 'properties': {'error': {'type': 'string'}, 'status': {'type': 'string'}, 'task_type': {'type': 'string'}, 'created_at': {'type': 'string'}, 'deliverable': {'type': 'object', 'properties': {'title': {'type': 'string'}, 'sections': {'type': 'array', 'items': {'type': 'object', 'properties': {'content': {'type': 'string'}, 'heading': {'type': 'string'}}}}}}, 'total_steps': {'type': 'number'}, 'workflow_id': {'type': 'string'}, 'completed_at': {'type': 'string'}, 'credits_used': {'type': 'number'}, 'current_step': {'type': 'number'}, 'quality_review': {'type': 'object', 'properties': {'score': {'type': 'number'}, 'summary': {'type': 'string'}, 'path_to_100': {'type': 'array', 'items': {'type': 'string'}}}}, 'generated_title': {'type': 'string'}, 'actual_steps_executed': {'type': 'number'}, 'completed_step_summaries': {'type': 'array', 'items': {'type': 'object', 'properties': {'step': {'type': 'number'}, 'tool': {'type': 'string'}, 'model': {'type': 'string'}, 'summary': {'type': 'string'}, 'framework': {'type': 'string'}}}}}}}}
输入模式
{'type': 'object', 'required': [], 'properties': {'q': {'type': 'string', 'description': 'Search the workflow title and task description. Every whitespace-separated term must appear in one or the other, as a case-insensitive substring — so "vector search postgres" matches a task described as "add vector search to an existing Postgres-backed SaaS app". Substring matching, not full-text: there is no stemming and no ranking, so "migrating" does not match "migration". Max 200 characters and 8 terms; punctuation is treated as a separator and wildcards are not supported.'}, 'limit': {'type': 'number', 'description': 'Page size (default 20, max 100)'}, 'cursor': {'type': 'string', 'description': 'Pagination cursor (created_at timestamp from previous page)'}, 'status': {'type': 'string', 'description': 'Filter by status (comma-separated). Valid values: executing, step_executing, completed, failed, halted, pending_approval, cancelled. E.g. "halted,failed,pending_approval"'}, 'folder_id': {'type': 'string', 'description': 'Filter by folder ID. Pass "unassigned" for workflows in no folder'}, 'task_type': {'type': 'string', 'description': 'Filter by classified task type'}, 'created_after': {'type': 'string', 'description': 'ISO timestamp — only workflows created after this time'}, 'created_before': {'type': 'string', 'description': 'ISO timestamp — only workflows created before this time'}, 'counts_toward_limit': {'enum': ['true', 'false'], 'type': 'string', 'description': 'Filter to workflows counting toward the concurrent limit'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'properties': {'ok': {'type': 'boolean'}, 'workflows': {'type': 'array', 'items': {'type': 'object', 'properties': {'status': {'type': 'string'}, 'task_type': {'type': 'string'}, 'created_at': {'type': 'string'}, 'started_at': {'type': 'string'}, 'total_steps': {'type': 'number'}, 'workflow_id': {'type': 'string'}, 'completed_at': {'type': 'string'}, 'current_step': {'type': 'number'}, 'task_excerpt': {'type': 'string'}, 'history_locked': {'type': 'boolean'}, 'credits_charged': {'type': 'number'}, 'generated_title': {'type': 'string'}, 'available_actions': {'type': 'array', 'items': {'type': 'string'}}, 'counts_toward_limit': {'type': 'boolean'}}}}, 'pagination': {'type': 'object', 'properties': {'limit': {'type': 'number'}, 'cursor': {'type': 'string'}, 'has_more': {'type': 'boolean'}, 'total_count': {'type': 'number'}}}, 'credits_remaining': {'type': 'number'}, 'concurrent_summary': {'type': 'object', 'properties': {'limit': {'type': 'number'}, 'active': {'type': 'number'}, 'remaining': {'type': 'number'}}}}}
近期工具变更
类似的 MCP 服务器
Delx Commerce — Pay-per-Result APIs for Agents
Provides pay-per-result APIs and agent protocol tools for continuity, multi-agent coordination, document OCR, and crypto-related …
SAP MCP Server
Provides an MCP gateway connecting SAP-related tools with Solana, DeFi, decentralized identity, and x402 payments.
TheProtocol — Sovereign AI Agent Platform
Manages sovereign AI agents, identities, contracts, payments, governance, exchanges, and cross-frame token transfers.
AIMEAT
Provides a self-hosted agent operating system with agent work delegation, access controls, federation, hooks, SSO, security admin…
hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
GPT55 Model Gateway
Acts as a remote model gateway exposing GPT chat, coding and review services, lightweight text utilities, and prepaid or x402-bas…
Rokha
Provides access to an agent-skill and MCP server registry, skill inspection and composition tools, OAuth connections, and agent a…
Japan Public Ledgers MCP
Provides agent identity, memory, audit, trust, proxy, temporary email, webhook, CAPTCHA, and alerting capabilities alongside publ…