Postman

Exposes generated Postman API requests as MCP-compatible tools for local or remote clients.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 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": {
    "marcellodesales-palo-alto-mcp-server": {
      "command": "node",
      "args": [
        "</absolute/path/to/mcpServer.js>"
      ],
      "env": {
        "ACME_API_KEY": "YOUR_API_KEY",
        "WIDGETS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You have an MCP server that exposes a programmable set of Postman API tools to MCP-compatible clients. It lets you run a local server that presents your selected Postman requests as callable tools, enabling automated workflows and chat-based integration with tools you choose to expose.

How to use

Install and run the MCP server, then connect it to your MCP client (such as Claude Desktop or a compatible tool). Start by ensuring your environment contains the required API keys and that you can reach the node runtime from your command line. Once the server is running, you will see a list of tools you generated in Postman available to the MCP client. You can invoke each tool from the client to perform the corresponding API request, and you can test each tool to confirm it uses the provided environment keys correctly.

How to install

Prerequisites you need before installation are clear: you must have Node.js version 18 or newer (v20+ is recommended) and npm (comes with Node). Ensure fetch is available in your Node version; if not, you can swap in node-fetch in the tool files and add node-fetch to your dependencies.

Step 1: Install dependencies from your project root.

Step 2: Create or update environment variables for the tools you generated. In your .env file, include keys for each workspace your tools come from. For example, if you have two workspaces Acme and Widgets, add these entries:

ACME_API_KEY=

WIDGETS_API_KEY=

Your server’s code uses these keys to authenticate requests. If you need to adapt the authentication method, you can modify the tools or environment at runtime.

Additional options

Docker deployment, standalone streaming, SSE, and stdio operation are supported. Use the commands shown below to start the server in each mode.

Docker deployment (production) lets you run the MCP server inside a container and connect via Claude Desktop.

Streamable HTTP enables the /mcp endpoint with streaming responses.

Server-Sent Events (SSE) provides real-time event streams via /sse and /messages.

Stdio mode runs the server through standard input/output, suitable for CLI or programmatic pipelines.

Configuration and tools

This MCP server exposes tools generated from your Postman API requests. You can inspect how environment keys are wired into each tool and verify that the correct API keys are used for each workspace.

{
  "type": "stdio",
  "name": "postman_mcp",
  "command": "node",
  "args": ["</absolute/path/to/mcpServer.js>"],
  "env": [
    {"name": "ACME_API_KEY", "value": "YOUR_API_KEY"},
    {"name": "WIDGETS_API_KEY", "value": "YOUR_API_KEY"}
  ]
}

Available tools

You can list and review all the generated tools to understand their descriptions and required parameters. For example, one tool might be named list_all_customers and retrieve a set of items with parameters such as a magic flag and a limit. Tools are exposed exactly as defined in your generated set.

Available tools

list_all_customers

Retrieve a list of useful things. Includes parameters such as magic and limit to control the results.