MCPForge — Turn Any OpenAPI REST API into an MCP Server

    1

    Give any AI agent instant access to any REST API: point MCPForge at an OpenAPI 3.x spec and get a working MCP server with zero hand-written integration code.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    MCPForge — Turn Any OpenAPI REST API into an MCP Server

    Example session with this skill installed

    Create an MCP server for the petstore-mini.yaml spec and tell me which tools it will provide.

    • Read your context and instructions
    • Compiled the mcpforge

    I have inspected the OpenAPI specification and prepared the MCP server configuration.

    MCP Server Inspection: petstore-mini.yaml

    Tool NameMethodPathDescriptionRequired Inputs
    listPetsGET/petsList all petslimit (optional)
    createPetPOST/petsCreate a new petname, tag
    getPetGET/pets/{id}Find pet by IDid
    deletePetDELETE/pets/{id}Delete a petid

    To run this server locally for Claude Desktop, use the following configuration in your claude_desktop_config.json:

    {
      "mcpServers": {
        "petstore": {
          "command": "mcpforge",
          "args": [
            "serve",
            "examples/petstore-mini.yaml",
            "--allow-private-hosts"
          ],
          "env": {
            "MCPFORGE_AUTH_ApiKeyAuth": "YOUR_API_KEY_HERE"
          }
        }
      }
    }
    

    Next steps

    • Set your API key in the MCPFORGE_AUTH_ApiKeyAuth environment variable.
    • Restart your MCP client to load the new tools.
    • Use the listPets tool to verify the connection to the API.
    petstore-mini.yaml

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Integrating third-party REST APIs into AI agents usually requires writing hundreds of lines of brittle glue code. MCPForge automates this by converting any OpenAPI 3.x specification into a functional Model Context Protocol (MCP) server instantly.

    What it does

    • Automated Tool Generation converts OpenAPI operations into MCP tools with full input schemas.
    • Dynamic Request Execution handles HTTP calls, parameter mapping, and JSON body serialization.
    • Security Scheme Mapping supports API Key, Bearer, and Basic authentication via environment variables.
    • SSRF Protection includes a built-in guard that blocks requests to private or loopback hosts by default.
    • Multi-Transport Support allows serving tools over standard I/O for local IDEs or SSE for remote clients.
    • Spec Filtering uses include and exclude lists to limit which API endpoints are exposed to the agent.

    How it works

    1. Inspect the API specification using mcpforge inspect to verify tools and required inputs.
    2. Configure credentials by setting environment variables matching the spec's security scheme names.
    3. Serve the MCP server using mcpforge serve pointing to a local file or a remote URL.
    4. Connect the server to an MCP-compatible client like Claude Desktop or Cursor using the stdio transport.

    Frameworks & tools

    Built with Python 3.10+, the official MCP Python SDK, httpx for asynchronous networking, and pyyaml for specification parsing.

    Why this beats prompting it yourself

    Manual prompting often fails to track complex API schemas or correct parameter types, leading to runtime errors. This skill provides a rigid, typed interface that ensures the agent follows the API specification exactly while handling the underlying networking and auth logic.

    Use cases

    • Connect Claude Desktop to internal microservices for data retrieval.
    • Give an AI agent the ability to manage Cloud or SaaS resources via REST.
    • Prototype AI-powered API clients without writing integration boilerplate.
    • Bridge local development APIs to Cursor for automated testing.

    Known limitations

    Does not support OAuth2 or OpenID Connect flows. Request bodies are limited to application/json and it does not support streaming responses or MCP resources.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    No support for OAuth2/OIDC or non-JSON request bodies. Tools only; no MCP resources or prompts. Requires Python 3.10+. Requests restricted to 1MB by default.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    Software
    PythonGit

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    This skill bridges the gap between LLMs and existing software by automatically transforming OpenAPI specifications into Model Context Protocol (MCP) servers, eliminating the need to write manual glue code for every API endpoint.

    The server works with any MCP-compatible client, including Claude Desktop and Cursor. It requires a environment running Python 3.10 or higher and supports any API that follows the OpenAPI 3.x standard.

    Setup is a simple four-step process: inspect your API spec, configure your credentials via environment variables, launch the server using the provided CLI, and link it to your preferred AI client via standard I/O.

    The skill currently supports API Key, Bearer Token, and Basic Auth; however, it does not support OAuth2 or OpenID Connect flows, and it is limited to JSON-based request bodies.

    Yes, the skill includes built-in SSRF protection that automatically blocks the agent from making requests to private or loopback hosts, ensuring your internal network remains secure.

    You receive the full MCPForge toolset, including the CLI for inspecting, configuring, and serving APIs, along with documentation for integrating with common AI IDEs and desktop clients.

    New in Agents & Orchestration