Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RRF_KNoReciprocal Rank Fusion constant for hybrid search.
SI_DATA_DIRNoShared data directory used by all MCPs in the pipeline. Set to the same absolute path for all servers.
DEFAULT_TOP_KNoDefault number of results returned by search_similar if top_k is not specified.
EMBED_BACKENDNoEmbedding backend: 'auto' uses sentence-transformers if available, otherwise falls back to the hashed n-gram TF-IDF backend.auto
MCP_HTTP_PORTNoPort for the HTTP transport server.8082
VECTOR_BACKENDNoVector store backend: 'auto' uses Chroma if available, otherwise falls back to the Numpy .npz + JSON backend.auto

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

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/anands-bounteous/historical-kb-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server