Smithery MCP server for AI agents
Let Claude, ChatGPT or your own agent read Smithery: 1 typed function through one MCP server. No Smithery API key needed.
- Site
- smithery.ai
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Smithery
An MCP server for Smithery 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/smitheryEvery site
One MCP server for Smithery 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
searchFull-text/semantic search over the Smithery MCP server registry.Arguments
Name Type Required querystring | ({ query: string } & SmitherySearchOptions)Yes options.pagenumberNo options.pageSizenumberNo options.verifiedbooleanNo options.remotebooleanNo options.isDeployedbooleanNo options.namespacestringNo interface SmitherySearchOptions { page?: number; pageSize?: number; verified?: boolean; remote?: boolean; isDeployed?: boolean; namespace?: string; }Returns
SmitherySearchResultinterface SmitheryServer { id: string; qualifiedName: string; namespace: string | null; slug: string | null; displayName: string; description: string; iconUrl: string | null; verified: boolean; useCount: number; remote: boolean | null; isDeployed: boolean; createdAt: string; homepage: string; bySmithery: boolean; owner: string | null; score: number | null; } interface SmitherySearchResult { servers: SmitheryServer[]; pagination: { currentPage: number; pageSize: number; totalPages: number; totalCount: number }; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/smithery/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.smithery.search({ query: "demo-mcp", pageSize: 3 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.smithery.search({"query": "demo-mcp", "pageSize": 3}))curl -X POST https://api.bowmark.ai/v1/sites/smithery/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":{"query":"demo-mcp","pageSize":3}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.smithery.search({ query: "demo-mcp", pageSize: 3 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/smithery/<function> - OpenAPI
/v1/sites/smithery/openapi.json