policy-rag-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RATE_LIMIT | No | Optional rate limit for /api/ask, e.g. 10/minute. | |
| POSTGRES_DB | No | PostgreSQL database name. | |
| DATABASE_URL | No | PostgreSQL connection string with pgvector support. For example, postgresql://user:password@host:5432/database. | |
| LANGFUSE_HOST | No | Optional Langfuse host URL, e.g. https://cloud.langfuse.com. | |
| POSTGRES_HOST | No | PostgreSQL host for local Docker or Neon. | |
| POSTGRES_PORT | No | PostgreSQL port. | |
| POSTGRES_USER | No | PostgreSQL username. | |
| POSTGRES_PASSWORD | No | PostgreSQL password. | |
| AZURE_OPENAI_MODEL | Yes | The generation model name, e.g. gpt-5-mini. | |
| LANGFUSE_PUBLIC_KEY | No | Optional Langfuse public key for tracing. | |
| LANGFUSE_SECRET_KEY | No | Optional Langfuse secret key for tracing. | |
| AZURE_OPENAI_API_KEY | Yes | API key for the Azure AI Foundry (Azure OpenAI compatible) resource. | |
| AZURE_EMBEDDING_MODEL | Yes | The embedding model name, e.g. text-embedding-3-small. | |
| AZURE_OPENAI_BASE_URL | Yes | Base URL for the Azure AI Foundry deployment, including the /openai/v1 path. For example, https://<resource>.services.ai.azure.com/openai/v1. |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues