MCP Server: Scalable OpenAPI Endpoint Discovery and API Request Tool

TODO

• The docker image is 2GB without pre-downloaded models. Its 3.76GB with pre-downloaded models!! Too big, someone please help me to reduce the size.

Configuration

Customize through environment variables. GLOBAL_TOOL_PROMPT is IMPORTANT!

• OPENAPI_JSON_DOCS_URL: URL to the OpenAPI specification JSON (defaults to https://api.staging.readymojo.com/openapi.json)
• MCP_API_PREFIX: Customizable tool namespace (default "any_openapi"):

  # Creates tools: custom_api_request_schema and custom_make_request
  docker run -e MCP_API_PREFIX=finance ...
  

• GLOBAL_TOOL_PROMPT: Optional text to prepend to all tool descriptions. This is crucial to make the Claude select and not select your tool accurately.

  # Adds "Access to insights apis for ACME Financial Services abc.com . " to the beginning of all tool descriptions
  docker run -e GLOBAL_TOOL_PROMPT="Access to insights apis for ACME Financial Services abc.com ." ...
  

TL'DR

Why I create this: I want to serve my private API, whose swagger openapi docs is a few hundreds KB in size.

• Claude MCP simply error on processing these size of file
• I attempted convert the result to YAML, not small enough and a lot of errors. FAILED
• I attempted to provide a API category, then ask MCP Client (Claude Desktop) to get the api doc by group. Still too big, FAILED.

Eventually I came down to this solution:

• It uses in-memory semantic search to find relevant Api endpoints by natural language (such as list products)
• It returns the complete end-point docs (as I designed it to store one endpoint as one chunk) in millionseconds (as it's in memory)

Boom, Claude now knows what API to call, with the full parameters!

Wait I have to create another tool in this server to make the actual restful request, because "fetch" server simply don't work, and I don't want to debug why.

https://github.com/user-attachments/assets/484790d2-b5a7-475d-a64d-157e839ad9b0

Technical highlights:

query -> [Embedding] -> FAISS TopK -> OpenAPI docs -> MCP Client (Claude Desktop)
MCP Client -> Construct OpenAPI Request -> Execute Request -> Return Response

Features

• 🧠 Use remote openapi json file as source, no local file system access, no updating required for API changes
• 🔍 Semantic search using optimized MiniLM-L3 model (43MB vs original 90MB)
• 🚀 FastAPI-based server with async support
• 🧠 Endpoint based chunking OpenAPI specs (handles 100KB+ documents), no loss of endpoint context
• ⚡ In-memory FAISS vector search for instant endpoint discovery

Limitations

• Not supporting linux/arm/v7 (build fails on Transformer library)
• 🐢 Cold start penalty (~15s for model loading) if not using docker image
• [Obsolete] Current docker image disabled downloading models. You have a dependency over huggingface. When you load the Claude Desktop, it takes some time to download the model. If huggingface is down, your server will not start.
• The latest docker image is embedding pre-downloaded models. If there is issues, I would revert to the old one.

Multi-instance config example

Here is the multi-instance config example. I design it so it can more flexibly used for multiple set of apis:

{
  "mcpServers": {
    "finance_openapi": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAPI_JSON_DOCS_URL=https://api.finance.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:la

... [View full README on GitHub](https://github.com/baryhuang/mcp-server-any-openapi#readme)