Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODEGRAPH_STATIC_MODELNoPath to the static embedding model directory. Used when --embedding-model static is enabled. If not set, the default location is used.~/.codegraph/static_models/jina-code-static-256
CODEGRAPH_TOOL_PROFILENoNarrows the exposed MCP tool surface to a named profile. Valid values: all, core, graph, memory, security. Overrides the --profile flag.all
CODEGRAPH_SKIP_MEMORY_CHECKNoSet to '1', 'true', or 'yes' to bypass the memory check before loading the ONNX embedding model. Useful when the machine has plenty of free RAM but the check fails due to reporting issues.

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/codegraph-ai/CodeGraph'

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