Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FORGE_URLNoGit provider base URL (not needed for github or local)
FORGE_TYPEYesSource type: forgejo, gitea, github, gitlab, or local
FORGE_USERNoYour username on the git provider
FORGE_TOKENNoAPI token with read access
OLLAMA_API_KEYNoAPI key for OpenAI-compatible APIs (optional)
OLLAMA_API_TYPENoAPI format: ollama or openaiollama
OLLAMA_BASE_URLNoOllama or OpenAI-compatible API URLhttp://localhost:11434
LOCAL_REPOS_PATHNoLocal folder to scan (when FORGE_TYPE=local)
OLLAMA_EMBED_MODELNoEmbedding model namenomic-embed-text
OLLAMA_FALLBACK_MODELNoFallback model (optional)
SYNAPTEX_EXCLUDE_DIRSNoLocal dirs to skip during scan (comma-separated)
SYNAPTEX_SEARCH_BACKENDNoSearch engine: embed, leann, or fts5embed
SYNAPTEX_INCLUDE_PATTERNSNoFiles to index per repo (comma-separated)CLAUDE.md

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/jeromelabophy-gif/Synaptex_claude'

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