Public APIs MCP

Instructions

Implementation Reference

• src/public_apis_mcp/tools.py:13-32 (handler)

  Core handler function implementing the embedding-based search for public APIs matching the query.
  def search_public_apis(query: str, limit: int = 5) -> list[SearchResult]: """Search for free public APIs that match the input query string.""" idx = ensure_index() qvec, _ = embed_query(query, model_id=idx.model_id) top = idx.search(qvec, top_k=max(1, min(50, int(limit)))) # limit to 50 items, by_id = load_catalog_indexed() results: list[SearchResult] = [] for api_id, score in top: item = by_id.get(api_id) if not item: continue results.append( SearchResult( id=item.id, name=item.api, score=float(score), snippet=item.description, ) ) return results
• src/public_apis_mcp/types.py:17-22 (schema)

  Pydantic schema for the SearchResult output type returned by the tool.
  class SearchResult(BaseModel): id: str name: str score: float snippet: str
• src/public_apis_mcp/tools.py:12-13 (registration)

  Registration of the tool using @mcp.tool decorator within register_tools function.
  @mcp.tool def search_public_apis(query: str, limit: int = 5) -> list[SearchResult]:
• src/public_apis_mcp/server.py:6-11 (registration)

  Imports register_tools and calls it to register the tools in the MCP server creation.
  from .tools import register_tools def create_server() -> FastMCP: mcp = FastMCP(name="free-api-mcp") register_tools(mcp)