MCPBuilder

Generate Model Context Protocol (MCP) servers from API specifications (OpenAPI/Postman) with web UI

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio unitoneai-mcpbuilder node /absolute/path/to/generated-servers/unitoneai-mcpbuilder/dist/index.js \
  --env API_TOKEN="your_bearer_token_here" \
  --env API_BASE_URL="https://api.example.com"

How to use

UNITONE MCP Builder transforms any API specification or documentation into a Model Context Protocol (MCP) server, and provides an intuitive admin portal to configure, generate, and deploy those servers. The tool parses OpenAPI/Swagger specs, Postman collections, or plain-text API docs to auto-generate MCP tools for each endpoint, including authentication and transport settings. Generated servers use STDIO transport, making them compatible with MCP clients across languages. Through the Admin Portal you can upload specs, select endpoints to expose, configure authentication, and deploy servers with a single click. The included MCP SDK integration helps ensure type-safe tool definitions for your endpoints, while automatic OpenAPI $ref resolution and path parameter handling simplify complex APIs. When you’re ready, you can generate a server, deploy it, and then point your MCP client at the produced server configuration to start making requests via natural language-enabled assistants.

How to install

Prerequisites:

Node.js >= 20.0.0
npm >= 9.0.0

Installation steps:

Clone the repository git clone https://github.com/UnitOneAI/MCPBuilder.git cd MCPBuilder
Install dependencies npm install
Start the development server npm run dev

Notes:

The frontend admin portal will be accessible (as configured in the project) and the API server will run alongside it. Ensure your environment has network access to fetch any required OpenAPI specs or Postman collections during parsing.
For production deployments, follow your hosting environment’s guidelines after generating servers via the admin portal.

Additional notes

Tips and considerations:

Local development is intended for single-user workflows. For enterprise or hosted deployments, contact UNITONE for enterprise solutions.
When configuring servers, remember to supply environment variables (e.g., API_BASE_URL, API_TOKEN) via the MCP client configuration; they can be automatically injected at runtime.
If you encounter issues parsing large OpenAPI specs, enable verbose logging in the portal to diagnose reference resolution or endpoint extraction problems.
Generated MCP servers rely on the STDIO transport; ensure your MCP client is configured to communicate over STDIO for compatibility.
Keep the MCPBuilder repository up-to-date to benefit from the latest tooling for tool generation and authentication support.

Related MCP Servers

mcp-graphql

364

Model Context Protocol server for GraphQL

rohlik

MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)

mcp -js

MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.

architect

A powerful, self-extending MCP server for dynamic AI tool orchestration. Features sandboxed JS execution, capability-based security, automated rate limiting, marketplace integration, and a built-in monitoring dashboard. Built for the Model Context Protocol (MCP).

alris

Alris is an AI automation tool that transforms natural language commands into task execution.

mode-manager

MCP Memory Agent Server - A VS Code chatmode and instruction manager with library integration