Use AI agents with the Postman API

The Postman Model Context Protocol (MCP) server enables AI agents like Claude, Cursor, and VS Code to help you manage your Postman resources, including workspaces, collections, specifications, mocks, and monitors. The server translates your natural language commands into API workflows behind the scenes. With MCP, you can build AI agents and complex workflows on top of LLMs using the tools and context provided by the servers.

Communication between the Postman API and the AI agent happens through the following methods:

  • STDIO - Runs the MCP server locally on the agent machine. Requires downloading and running the source code yourself or spinning up a local Docker image.
  • Streamable HTTP - Securely links the agent to the server over HTTPS at https://mcp.postman.com/mcp, without requiring any extra agent setup. Great for using the Postman MCP server with your preferred IDE or AI agent. It supports two tool configurations to better serve different use cases:
    • Minimal - Only includes essential tools for basic Postman operations, available at https://mcp.postman.com/minimal. This offers faster performance and simplifies use for those who only need basic Postman operations.
    • Full - Includes all available Postman API tools (100+ tools), available at https://mcp.postman.com/mcp.

Get started with agents

Follow the Postman MCP server setup guide to get up and running. Then, explore best practices and tips for getting the most out of its features.

Last modified: 2025/08/19