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). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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