Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HTTP_PORTNoPort for the upload server and MCP SSE endpoint.3001
CHUNK_SIZENoBackward-compatible chunk size.3000
STORAGE_NAMENoStorage provider name (e.g., chroma).chroma
CHUNKING_NAMENoChunking provider name: langchain, chonkie, or builtin.langchain
CHUNK_OVERLAPNoBackward-compatible chunk overlap.150
MAX_CHUNK_SIZENoBackward-compatible maximum chunk size.5000
EMBEDDINGS_NAMENoEmbeddings provider name (e.g., xenova, transformersjs).xenova
STORAGE_OPTIONSNoJSON string of provider-specific storage options.{"url":"http://localhost:8000"}
CHUNKING_OPTIONSNoJSON string of provider-specific chunking options.{"strategy":"recursive","chunkSize":3000,"chunkOverlap":150}
EMBEDDINGS_OPTIONSNoJSON string of provider-specific embedding options.{"model":"Xenova/all-MiniLM-L6-v2","maxBatchSize":50}

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/bsreeram08/Cogni-Docs'

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