OpenAPI to

Converts OpenAPI specifications into an MCP server to expose APIs as AI-accessible tools.

typescript

GitHub Stars

typescript

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": {
    "tyktechnologies-api-to-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tyk-technologies/api-to-mcp@latest",
        "--spec",
        "https://petstore3.swagger.io/api/v3/openapi.json"
      ],
      "env": {
        "API_KEY": "<API_KEY>",
        "HEADER_*": "<HEADER_*>",
        "CONFIG_FILE": "<CONFIG_FILE>",
        "DISABLE_X_MCP": "<DISABLE_X_MCP>",
        "CUSTOM_HEADERS": "<CUSTOM_HEADERS>",
        "OPENAPI_SPEC_PATH": "<OPENAPI_SPEC_PATH>",
        "TARGET_API_BASE_URL": "<TARGET_API_BASE_URL>",
        "SECURITY_CREDENTIALS": "<SECURITY_CREDENTIALS>",
        "SECURITY_SCHEME_NAME": "<SECURITY_SCHEME_NAME>",
        "OPENAPI_OVERLAY_PATHS": "<OPENAPI_OVERLAY_PATHS>",
        "MCP_BLACKLIST_OPERATIONS": "<MCP_BLACKLIST_OPERATIONS>",
        "MCP_WHITELIST_OPERATIONS": "<MCP_WHITELIST_OPERATIONS>"
      }
    }
  }
}

You turn an OpenAPI specification into a dynamic MCP server so an AI assistant can interact with your API. This lets you expose API operations as MCP tools, enabling natural, tool-powered conversations with your services while preserving authentication, headers, and parameter semantics.

How to use

Start by running an MCP server that loads your OpenAPI spec. You will configure the server to expose API operations as MCP tools, then connect your AI assistant to the MCP endpoint. The tool supports creating multiple MCP servers from OpenAPI specs, including remote and local specs, overlays, and operation whitelisting. Use the MCP client in your AI workflow to fetch available tools, then invoke them to interact with your API.

How to install

Prerequisites: You need Node.js installed on your computer.

Install and run the MCP server using the npm-based command shown in the configuration examples. You will typically use npx to run the server with your OpenAPI spec.

Configuration

Configure how the OpenAPI spec is loaded, which operations are exposed, and how requests are routed. You can load an OpenAPI spec from a local file or a remote URL, apply overlays, narrow the exposed operations with a whitelist, and set a target API base URL. You can also customize HTTP headers to send with every API call and control the X-MCP header behavior.

Notes and tips

To use the OpenAPI to MCP server with a client you can load an MCP tool set from a local project or run it as a standalone service. - If you need to customize the exposure, you can adjust overlays and whitelist patterns to precisely control which operations appear as MCP tools. - Environment variables and CLI options let you influence headers, authentication, and the target API base URL. - The server preserves parameter formats and location metadata to keep requests compatible with your API.

Built by

VeilStrat

AI signals for GTM teams