Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MODELYesName of the LLM model to use (e.g., Qwen2.5-Coder-3B-Instruct)
CARGO_PATHNoPath to the cargo executable (e.g., /usr/bin/cargo)
LLM_API_KEYYesAPI key for the LLM service
QDRANT_HOSTNoHostname of the Qdrant vector databaselocalhost
QDRANT_PORTNoPort of the Qdrant vector database6333
LLM_API_BASEYesBase URL of the LLM API server (e.g., http://localhost:8080/v1)
LLM_EMBED_SIZENoDimension size of the embedding vectors768
LLM_EMBED_MODELYesName of the embedding model (e.g., nomic-embed)
RUST_COMPILER_PATHNoPath to the rustc executable (e.g., /usr/bin/rustc)
SKIP_VECTOR_SEARCHNoSet to 'false' to enable vector search with Qdranttrue

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/cardea-mcp/RustCoder'

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