此 MCP 可以做什么
Convenes multiple AI models to debate coding, debugging, architecture, implementation, tradeoff, and code-review questions.
工具
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['decision'], 'properties': {'context': {'type': 'string', 'maxLength': 50000, 'description': 'Background context â\x80\x94 codebase, team, timeline, constraints'}, 'options': {'type': 'array', 'items': {'type': 'string'}, 'minItems': 2, 'description': 'Specific options to compare'}, 'decision': {'type': 'string', 'maxLength': 10000, 'minLength': 1, 'description': 'The decision or question to evaluate'}, 'priorities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'What matters most (e.g., ["performance", "dx", "cost"])'}, 'webhook_url': {'type': 'string', 'format': 'uri', 'description': 'Webhook URL to POST results to after completion'}, 'thinking_level': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'default': 'medium', 'description': 'Analysis depth'}, 'session_context': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 3, 'description': 'Session IDs to use as context (max 3). Prior moderator summaries will be prepended.'}}}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'verbose': {'type': 'boolean', 'default': False, 'description': 'Include detailed per-window rate limit breakdown'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['credits', 'plan', 'rateLimits', 'status'], 'properties': {'plan': {'type': 'string', 'description': 'Current plan tier'}, 'status': {'type': 'string', 'description': 'Overall usage status'}, 'credits': {'type': 'number', 'description': 'Remaining credit balance'}, 'rateLimits': {'type': 'object', 'required': ['daily', 'fiveHour', 'weekly'], 'properties': {'daily': {'type': 'object', 'required': ['count', 'limit', 'resetAt'], 'properties': {'count': {'type': 'number', 'description': 'Requests used'}, 'limit': {'type': 'number', 'description': 'Request cap'}, 'resetAt': {'type': 'string', 'description': 'Reset timestamp'}}, 'description': 'Daily rate limit window', 'additionalProperties': False}, 'weekly': {'type': 'object', 'required': ['count', 'limit', 'resetAt'], 'properties': {'count': {'type': 'number', 'description': 'Requests used'}, 'limit': {'type': 'number', 'description': 'Request cap'}, 'resetAt': {'type': 'string', 'description': 'Reset timestamp'}}, 'description': 'Weekly rate limit window', 'additionalProperties': False}, 'fiveHour': {'type': 'object', 'required': ['count', 'limit', 'resetAt'], 'properties': {'count': {'type': 'number', 'description': 'Requests used'}, 'limit': {'type': 'number', 'description': 'Request cap'}, 'resetAt': {'type': 'string', 'description': 'Reset timestamp'}}, 'description': '5-hour rate limit window', 'additionalProperties': False}}, 'description': 'Rate limit status across all windows', 'additionalProperties': False}}, 'additionalProperties': False}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['prompt'], 'properties': {'mode': {'enum': ['analyzing', 'brainstorming', 'debating', 'solving'], 'type': 'string', 'default': 'debating', 'description': 'Conversation mode: analyzing (research), brainstorming (ideas), debating (tradeoffs), solving (action plans)'}, 'roles': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Inline role names for participants (e.g., ["Security Architect", "Backend Engineer"])'}, 'format': {'enum': ['discussion', 'adr', 'comparison', 'pros-cons'], 'type': 'string', 'default': 'discussion', 'description': 'Moderator output format: discussion (narrative), adr (architecture decision), comparison (table), pros-cons'}, 'models': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 6, 'minItems': 3, 'description': 'Override specific model IDs. Min 3 models. Use list-models to see available options'}, 'prompt': {'type': 'string', 'maxLength': 10000, 'minLength': 1, 'description': 'The question, topic, or problem to debate'}, 'context': {'type': 'string', 'maxLength': 50000, 'description': 'Additional background context for the debate (code, docs, requirements)'}, 'knowledge': {'type': 'array', 'items': {'type': 'object', 'required': ['content', 'type'], 'properties': {'type': {'enum': ['text', 'url'], 'type': 'string', 'description': 'Content type: text (pass-through) or url (fetch and extract)'}, 'label': {'type': 'string', 'description': 'Label for this knowledge item'}, 'content': {'type': 'string', 'description': 'Text content or URL to fetch'}}}, 'maxItems': 5, 'description': 'Reference knowledge to inject as context'}, 'auto_route': {'type': 'boolean', 'default': False, 'description': 'Auto-select optimal models based on prompt analysis and historical performance'}, 'webhook_url': {'type': 'string', 'format': 'uri', 'description': 'Webhook URL to POST results to after completion'}, 'thinking_level': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'default': 'medium', 'description': 'Controls model quality and cost: low (fast/cheap), medium (balanced), high (maximum reasoning)'}, 'session_context': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 3, 'description': 'Session IDs to use as context (max 3). Prior moderator summaries will be prepended.'}}}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['problem'], 'properties': {'code': {'type': 'string', 'maxLength': 100000, 'description': 'The relevant code where the bug occurs'}, 'error': {'type': 'string', 'maxLength': 10000, 'description': 'Error message, stack trace, or unexpected output'}, 'problem': {'type': 'string', 'maxLength': 10000, 'minLength': 1, 'description': 'Describe the bug, failure, or unexpected behavior'}, 'knowledge': {'type': 'array', 'items': {'type': 'object', 'required': ['content', 'type'], 'properties': {'type': {'enum': ['text', 'url'], 'type': 'string', 'description': 'Content type: text (pass-through) or url (fetch and extract)'}, 'label': {'type': 'string', 'description': 'Label for this knowledge item'}, 'content': {'type': 'string', 'description': 'Text content or URL to fetch'}}}, 'maxItems': 5, 'description': 'Reference knowledge to inject as context'}, 'webhook_url': {'type': 'string', 'format': 'uri', 'description': 'Webhook URL to POST results to after completion'}, 'thinking_level': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'default': 'medium', 'description': 'Analysis depth'}, 'session_context': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 3, 'description': 'Session IDs to use as context (max 3). Prior moderator summaries will be prepended.'}, 'expected_behavior': {'type': 'string', 'maxLength': 5000, 'description': 'What should happen vs what actually happens'}}}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['description'], 'properties': {'scale': {'enum': ['startup', 'growth', 'enterprise'], 'type': 'string', 'default': 'startup', 'description': 'Target scale: startup (small team), growth (scaling), enterprise (large org)'}, 'tech_stack': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Preferred technologies'}, 'description': {'type': 'string', 'maxLength': 10000, 'minLength': 1, 'description': 'What the system should do'}, 'focus_areas': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Priority areas (e.g., ["security", "performance"])'}, 'webhook_url': {'type': 'string', 'format': 'uri', 'description': 'Webhook URL to POST results to after completion'}}}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'event': {'type': 'string', 'description': 'Filter by event name (e.g., "debate_completed")'}, 'level': {'enum': ['info', 'warn', 'error'], 'type': 'string', 'description': 'Filter by log level'}, 'limit': {'type': 'integer', 'default': 50, 'maximum': 200, 'minimum': 1, 'description': 'Max results'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Pagination offset'}, 'end_time': {'type': 'number', 'description': 'End timestamp (ms) for time range filter'}, 'session_id': {'type': 'string', 'description': 'Filter logs for a specific session'}, 'start_time': {'type': 'number', 'description': 'Start timestamp (ms) for time range filter'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['logs'], 'properties': {'logs': {'type': 'array', 'items': {'type': 'object', 'required': ['data', 'event', 'level', 'sessionId', 'time'], 'properties': {'data': {'anyOf': [{'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'anyOf': [{'type': 'string'}, {'type': 'number'}, {'type': 'boolean'}, {'type': 'null'}]}}, {'type': 'null'}], 'description': 'Structured log data payload'}, 'time': {'type': 'string', 'description': 'Log timestamp'}, 'event': {'type': 'string', 'description': 'Event name'}, 'level': {'type': 'string', 'description': 'Log severity level'}, 'sessionId': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Associated session identifier'}}, 'description': 'Log entry', 'additionalProperties': False}, 'description': 'Matching log entries'}}, 'additionalProperties': False}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'minLength': 1, 'description': 'The session ID to retrieve'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['createdAt', 'durationMs', 'id', 'prompt', 'qualityScore', 'toolName', 'totalCredits'], 'properties': {'id': {'type': 'string', 'description': 'Session identifier'}, 'prompt': {'type': 'string', 'description': 'Original prompt text'}, 'toolName': {'type': 'string', 'description': 'Tool that was invoked'}, 'createdAt': {'type': 'string', 'description': 'Session creation timestamp'}, 'durationMs': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'description': 'Duration in milliseconds'}, 'qualityScore': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'description': 'AI-rated quality score'}, 'totalCredits': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'description': 'Total credits consumed'}}, 'additionalProperties': False}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'minLength': 1, 'description': 'The session ID to get the thread link for'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['dashboardUrl', 'isPublic', 'publicUrl'], 'properties': {'isPublic': {'type': 'boolean', 'description': 'Whether the thread is publicly accessible'}, 'publicUrl': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Public share URL if thread is public'}, 'dashboardUrl': {'type': 'string', 'description': 'Dashboard URL to view the thread'}}, 'additionalProperties': False}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'thinking_level': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'description': 'Filter to a specific thinking level'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['levels'], 'properties': {'levels': {'type': 'array', 'items': {'type': 'object', 'required': ['label', 'level', 'models', 'moderator'], 'properties': {'label': {'type': 'string', 'description': 'Human-readable tier name'}, 'level': {'type': 'string', 'description': 'Thinking level identifier'}, 'models': {'type': 'array', 'items': {'type': 'object', 'required': ['capabilities', 'id', 'multiplier'], 'properties': {'id': {'type': 'string', 'description': 'Model identifier'}, 'multiplier': {'type': 'number', 'description': 'Credit cost multiplier'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Model capabilities'}}, 'description': 'Available model', 'additionalProperties': False}, 'description': 'Models in this tier'}, 'moderator': {'type': 'object', 'required': ['id', 'multiplier'], 'properties': {'id': {'type': 'string', 'description': 'Moderator model identifier'}, 'multiplier': {'type': 'number', 'description': 'Credit cost multiplier'}}, 'description': 'Moderator model for this tier', 'additionalProperties': False}}, 'description': 'Thinking level tier', 'additionalProperties': False}, 'description': 'Available thinking level tiers'}}, 'additionalProperties': False}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 100, 'minimum': 1, 'description': 'Max results to return'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 9007199254740991, 'minimum': 0, 'description': 'Pagination offset'}, 'tool_name': {'type': 'string', 'description': 'Filter by tool name (e.g., "consult", "architect")'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['hasMore', 'sessions'], 'properties': {'hasMore': {'type': 'boolean', 'description': 'Whether more results are available'}, 'sessions': {'type': 'array', 'items': {'type': 'object', 'required': ['credits', 'durationMs', 'id', 'prompt', 'thinkingLevel', 'toolName'], 'properties': {'id': {'type': 'string', 'description': 'Session identifier'}, 'prompt': {'type': 'string', 'description': 'Original prompt text'}, 'credits': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'description': 'Credits consumed'}, 'toolName': {'type': 'string', 'description': 'Tool that was invoked'}, 'durationMs': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'description': 'Duration in milliseconds'}, 'thinkingLevel': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Thinking level used'}}, 'description': 'Session entry', 'additionalProperties': False}, 'description': 'List of sessions'}}, 'additionalProperties': False}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['feature'], 'properties': {'feature': {'type': 'string', 'maxLength': 10000, 'minLength': 1, 'description': 'The feature or change to plan'}, 'knowledge': {'type': 'array', 'items': {'type': 'object', 'required': ['content', 'type'], 'properties': {'type': {'enum': ['text', 'url'], 'type': 'string', 'description': 'Content type: text (pass-through) or url (fetch and extract)'}, 'label': {'type': 'string', 'description': 'Label for this knowledge item'}, 'content': {'type': 'string', 'description': 'Text content or URL to fetch'}}}, 'maxItems': 5, 'description': 'Reference knowledge to inject as context'}, 'tech_stack': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Current tech stack'}, 'constraints': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Constraints (e.g., ["no breaking changes", "must support offline"])'}, 'webhook_url': {'type': 'string', 'format': 'uri', 'description': 'Webhook URL to POST results to after completion'}, 'thinking_level': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'default': 'medium', 'description': 'Planning depth'}, 'session_context': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 3, 'description': 'Session IDs to use as context (max 3). Prior moderator summaries will be prepended.'}, 'codebase_context': {'type': 'string', 'maxLength': 50000, 'description': 'Relevant existing code, file structure, or architecture notes'}}}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['code'], 'properties': {'code': {'type': 'string', 'maxLength': 100000, 'minLength': 1, 'description': 'The code to review'}, 'focus': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Review focus areas (e.g., ["security", "performance"])'}, 'language': {'type': 'string', 'description': 'Programming language (auto-detected if not specified)'}, 'webhook_url': {'type': 'string', 'format': 'uri', 'description': 'Webhook URL to POST results to after completion'}, 'thinking_level': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'default': 'medium', 'description': 'Review depth: low (quick scan), medium (balanced), high (thorough)'}}}
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['is_public', 'session_id'], 'properties': {'is_public': {'type': 'boolean', 'description': 'Set to true to make the thread publicly accessible, false to make it private'}, 'session_id': {'type': 'string', 'minLength': 1, 'description': 'The session ID from a previous debate'}}}
输出模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['isPublic', 'publicUrl'], 'properties': {'isPublic': {'type': 'boolean', 'description': 'Current visibility state'}, 'publicUrl': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'description': 'Public share URL if thread is public'}}, 'additionalProperties': False}
近期工具变更
类似的 MCP 服务器
Andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
IA-QA — 130+ QA & Dev Tools for AI Agents
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
CompletionKit
Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…
Replicate
Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…
Huggingface
Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.
Ai Model Experiments
Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.
rubrkit
Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.
Hipocampo MCP
Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…