Glama MCP server for AI agents
Let Claude, ChatGPT or your own agent read Glama: 1 typed function through one MCP server. No Glama API key needed.
- Site
- glama.ai
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Glama
An MCP server for Glama alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/glamaEvery site
One MCP server for Glama and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
searchSearches Glama's MCP server directory and returns matching rows from both its own indexed catalogue and its live federated registry query.Arguments
Name Type Required querystring | { query: string }Yes Returns
GlamaSearchResultinterface GlamaListedServer { namespace: string; slug: string; name: string; title: string; description: string | null; githubRepositoryFullName: string | null; githubStargazersCount: number | null; npmPackageName: string | null; toolCount: number; url: string; } interface GlamaRemoteServer { name: string; namespace: string; slug: string; title: string; description: string | null; githubRepositoryFullName: string | null; githubStargazersCount: number | null; healthy: boolean | null; url: string; } interface GlamaSearchResult { servers: GlamaListedServer[]; remoteServers: GlamaRemoteServer[]; hasMoreServers: boolean; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/glama/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.glama.search({ query: "stripe" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.glama.search({"query": "stripe"}))curl -X POST https://api.bowmark.ai/v1/sites/glama/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":{"query":"stripe"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.glama.search({ query: "stripe" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/glama/<function> - OpenAPI
/v1/sites/glama/openapi.json