Skip to main content
Glama
VarunJaiswal05

policy-rag-mcp-server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RATE_LIMITNoOptional rate limit for /api/ask, e.g. 10/minute.
POSTGRES_DBNoPostgreSQL database name.
DATABASE_URLNoPostgreSQL connection string with pgvector support. For example, postgresql://user:password@host:5432/database.
LANGFUSE_HOSTNoOptional Langfuse host URL, e.g. https://cloud.langfuse.com.
POSTGRES_HOSTNoPostgreSQL host for local Docker or Neon.
POSTGRES_PORTNoPostgreSQL port.
POSTGRES_USERNoPostgreSQL username.
POSTGRES_PASSWORDNoPostgreSQL password.
AZURE_OPENAI_MODELYesThe generation model name, e.g. gpt-5-mini.
LANGFUSE_PUBLIC_KEYNoOptional Langfuse public key for tracing.
LANGFUSE_SECRET_KEYNoOptional Langfuse secret key for tracing.
AZURE_OPENAI_API_KEYYesAPI key for the Azure AI Foundry (Azure OpenAI compatible) resource.
AZURE_EMBEDDING_MODELYesThe embedding model name, e.g. text-embedding-3-small.
AZURE_OPENAI_BASE_URLYesBase 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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources