Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOOM_MODELNoModel identifier for model-manifest context (optional)
LOOM_CLIENTNoClient adapter hint (optional): claude-code, gemini-cli, etc.
LOOM_CONTEXT_DIRNoPath to agent's context directory (default: ~/.config/loom/default)~/.config/loom/default
LOOM_SQLITE_DB_PATHNoOverride the memory DB path (default: <context>/memories.db)<context>/memories.db
LOOM_FASTEMBED_MODELNofastembed model ID (default: fast-bge-small-en-v1.5)fast-bge-small-en-v1.5
LOOM_FASTEMBED_CACHE_DIRNoWhere to cache ONNX models (default: ~/.cache/loom/fastembed/)~/.cache/loom/fastembed/

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/jbarket/loom'

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