Any OpenAPI

Provides scalable OpenAPI endpoint discovery and in-memory API requests via semantic search for private APIs.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-baryhuang_mcp-server-any-openapi": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAPI_JSON_DOCS_URL=https://api.finance.com/openapi.json",
        "-e",
        "MCP_API_PREFIX=finance",
        "buryhuang/mcp-server-any-openapi:latest"
      ],
      "env": {
        "MCP_API_PREFIX": "finance",
        "OPENAPI_JSON_DOCS_URL": "https://api.finance.com/openapi.json"
      }
    }
  }
}

You deploy an MCP server that discovers and uses OpenAPI endpoints through semantic search and in-memory processing. It lets you locate relevant API endpoints from a remote OpenAPI document set, then construct and execute requests against those endpoints efficiently, all within an MCP-enabled client workflow.

How to use

Set up the MCP server with the multi-instance configuration to expose separate API sources. You will then access tools that help you discover matching API endpoints and perform requests.

How to install

Prerequisites you need to install first: Docker and a modern container runtime. You may also install via a direct Python or npm setup if you prefer a source-based run, but using Docker is the simplest path for beginners.

Install and run the MCP server using the multi-instance configuration example that exposes two OpenAPI sources. You will start the respective containers with the required environment variables set.

{
  "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",
        "buryhuang/mcp-server-any-openapi:latest"
      ]
    },
    "healthcare_openapi": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAPI_JSON_DOCS_URL=https://api.healthcare.com/openapi.json",
        "-e",
        "MCP_API_PREFIX=healthcare",
        "buryhuang/mcp-server-any-openapi:latest"
      ]
    }
  }
}

Configuration

The server is configured through environment variables provided to each container. Use the following for the finance and healthcare instances:

{
  "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",
        "buryhuang/mcp-server-any-openapi:latest"
      ]
    }
  }
}

Troubleshooting and notes

The MCP server uses in-memory FAISS vector search and endpoint-centric processing to handle large OpenAPI specs efficiently. If you see startup delays, ensure the environment can download or access the OpenAPI JSON document and that the container has network access.

Additional considerations

You can tailor the namespace for the MCP tools with MCP_API_PREFIX. For finance, tools will be exposed as finance_api_request_schema and finance_make_request, enabling you to query endpoint details and execute requests programmatically.

OpenAPI-driven tools you will use

Two core tools are exposed under your chosen prefix to interact with the discovered APIs.

finance_api_request_schema: Get API endpoint schemas that match your intent. Returns endpoint details including path, method, parameters, and response formats.

finance_make_request: Execute a fully specified HTTP request against a selected endpoint, returning status, headers, and the response body.

Available tools

finance_api_request_schema

Get endpoint schemas that match your intent. Returns endpoint details including path, method, parameters, and response formats.

finance_make_request

Execute a fully specified HTTP request against a selected endpoint, returning status, headers, and the response body.

Built by

VeilStrat

AI signals for GTM teams