Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_RRF_KNoRRF k parameter (lower = more weight on top ranks)60
MCP_SSE_PORTNoMCP SSE endpoint port8081
MCP_WEB_PORTNoWeb UI port8080
MCP_DOCS_PATHNoPath to .md files inside container/docs
MCP_GIT_TOKENNoGitHub token for private repos
MCP_TRANSPORTNoMCP transport: 'sse' or 'stdio'sse
MCP_GIT_BRANCHNoBranch to syncmain
MCP_GIT_REPO_URLNoKnowledge repo URL (enables git sync)
MCP_GIT_AUTO_PUSHNoAuto-commit + push bugfix summariestrue
MCP_MIN_RELEVANCENoMinimum relevance % to return (0 = no filter)0
MCP_CHUNK_STRATEGYNoChunking strategy: 'heading', 'fixed', or 'hybrid'heading
MCP_RERANKER_MODELNoReranker model namecross-encoder/ms-marco-MiniLM-L-6-v2
MCP_WEBHOOK_SECRETNoGitHub webhook secret (enables /webhook/github HMAC verification)
MCP_EMBEDDING_MODELNoEmbedding model nameall-MiniLM-L6-v2
MCP_RRF_BM25_WEIGHTNoBM25 keyword search weight in RRF fusion1.0
MCP_RERANKER_ENABLEDNoEnable cross-encoder reranker for higher precisionfalse
MCP_GIT_SYNC_INTERVALNoPull interval in seconds (0 = disabled)300
MCP_RRF_VECTOR_WEIGHTNoVector search weight in RRF fusion1.0
MCP_EMBEDDING_PROVIDERNoEmbedding provider: 'local' (free, private) or 'openai'local

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/dl4rce/flaiwheel'

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