Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATABASE_URLYesPostgreSQL DSN. Requires the pgvector extension. Use a sync postgresql:// DSN (psycopg2), not +asyncpg.postgresql://…/agentic_rag
COHERE_API_KEYNoAPI key for Cohere reranking when using the cloud profile.
OPENAI_API_KEYNoAPI key for OpenAI-compatible cloud model endpoints when using the cloud profile.
ENABLE_API_DOCSNoSet to true to expose the full OpenAPI reference at /docs.false
FOLIO_STORAGE_ROOTNoDirectory that holds storage/ (uploaded files and the console session secret).the project root
FOLIO_REVOCATION_ENABLEDNoTurn the MCP Gate revocation feed on so revoked tokens stop working before they expire.false
FOLIO_JOB_TIMEOUT_SECONDSNoRuntime override for the indexing job timeout. Default comes from rag.indexing.
FOLIO_INDEXING_CONCURRENCYNoRuntime override for the indexing concurrency limit. Default comes from rag.indexing.
FOLIO_REVOCATION_CLIENT_IDNoResource-server client ID registered in MCP Gate for the revocation feed.
FOLIO_PER_FILE_TIMEOUT_SECONDSNoRuntime override for the per-file indexing timeout. Default comes from rag.indexing.
FOLIO_REVOCATION_CLIENT_SECRETNoClient secret for the revocation feed. Must be supplied via environment variable.

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