mcp-server-any-openapi
by baryhuang·★ 82·Score 40
An MCP server enabling Claude to discover and call any API endpoint through semantic search of OpenAPI specifications.
Overview
This MCP server processes OpenAPI specifications by chunking them into individual endpoints and creating an in-memory vector search index using FAISS. It enables Claude to discover relevant API endpoints through natural language queries and then execute actual API requests. The server handles large API documents efficiently through optimized MiniLM-L3 embeddings and endpoint-centric processing, making it ideal for integrating private APIs with Claude Desktop.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this server when you need to integrate private APIs with Claude Desktop and your OpenAPI specifications are too large for standard MCP implementations to handle.
When NOT to choose this
Avoid this if you need to support architectures other than linux/amd64 and linux/arm64, or if you can't tolerate the ~15s cold start penalty for model loading.
Tools this server exposes
2 tools extracted from the READMEany_openapi_api_request_schemaquery: stringGet API endpoint schemas that match your intent. Returns endpoint details including path, method, parameters, and response formats.
any_openapi_make_requestmethod: string, url: string, headers: object, query_params: object, body: objectMake HTTP requests to API endpoints with full control over request parameters.
Comparable tools
Installation
Installing via Smithery
npx -y @smithery/cli install @baryhuang/mcp-server-any-openapi --client claudeUsing pip
pip install mcp-server-any-openapiClaude Desktop Configuration
{
"mcpServers": {
"any_openapi": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"OPENAPI_JSON_DOCS_URL=https://api.example.com/openapi.json",
"-e",
"MCP_API_PREFIX=finance",
"-e",
"GLOBAL_TOOL_PROMPT='Access to insights apis for ACME Financial Services abc.com .",
"buryhuang/mcp-server-any-openapi:latest"
]
}
}
}FAQ
- How does this server handle large OpenAPI specifications?
- It chunks OpenAPI specs into individual endpoints and creates an in-memory FAISS vector search index, allowing it to efficiently process specifications up to 10MB (~5,000 endpoints).
- What platforms are supported by this MCP server?
- The Docker images support linux/amd64 and linux/arm64 platforms. It's noted that linux/arm/v7 is not supported due to build failures with the Transformer library.
Compare mcp-server-any-openapi with
Last updated · Auto-generated from public README + GitHub signals.