AI Governance MCP Server
by jason21wc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_GOVERNANCE_INDEX_PATH | No | Path to generated index. Required for pip installations when not running from project root. | |
| GOVERNANCE_RECENCY_WINDOW | No | Number of tool calls before governance expires. | 50 |
| AI_CONTEXT_ENGINE_READONLY | No | Read-only setting (true, false, auto). | auto |
| AI_CONTEXT_ENGINE_INDEX_MODE | No | Index mode (ondemand or realtime). | realtime |
| AI_CONTEXT_ENGINE_INDEX_PATH | No | Path for context engine indexes. | ~/.context-engine/indexes |
| AI_GOVERNANCE_DOCUMENTS_PATH | No | Path to governance documents. Required for pip installations when not running from project root. | |
| AI_GOVERNANCE_EMBEDDING_MODEL | No | Embedding model for semantic similarity. | BAAI/bge-small-en-v1.5 |
| AI_GOVERNANCE_SEMANTIC_WEIGHT | No | Weight for semantic search vs keyword search (0-1). | 0.6 |
| GOVERNANCE_ENFORCEMENT_ENABLED | No | Master toggle for enforcement. | true |
| GOVERNANCE_ENFORCEMENT_SOFT_MODE | No | Warn instead of block. Default true in generated configs. | true |
| AI_CONTEXT_ENGINE_EMBEDDING_MODEL | No | Embedding model for context engine. | BAAI/bge-small-en-v1.5 |
| AI_CONTEXT_ENGINE_SEMANTIC_WEIGHT | No | Semantic weight for context engine. | 0.7 |
| AI_CONTEXT_ENGINE_COGNEE_LLM_MODEL | No | Model name for knowledge graph LLM (optional). | |
| AI_CONTEXT_ENGINE_COGNEE_LLM_API_KEY | No | API key for knowledge graph cloud providers (optional). | |
| AI_CONTEXT_ENGINE_COGNEE_LLM_ENDPOINT | No | Custom endpoint for knowledge graph LLM (optional). | |
| AI_CONTEXT_ENGINE_COGNEE_LLM_PROVIDER | No | LLM provider for knowledge graph (optional). | ollama |
| AI_CONTEXT_ENGINE_EMBEDDING_DIMENSIONS | No | Embedding dimensions for context engine. | 384 |
| AI_CONTEXT_ENGINE_COGNEE_EMBEDDING_MODEL | No | Embedding model for knowledge graph (optional, falls back to context engine model). | |
| AI_CONTEXT_ENGINE_COGNEE_LLM_TEMPERATURE | No | LLM temperature for knowledge graph (optional). | 0.0 |
| AI_CONTEXT_ENGINE_COGNEE_EMBEDDING_PROVIDER | No | Embedding provider for knowledge graph (optional). | fastembed |
| AI_CONTEXT_ENGINE_COGNEE_EMBEDDING_DIMENSIONS | No | Embedding dimensions for knowledge graph (optional, falls back to context engine). |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jason21wc/ai-governance-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server