Postman Agent Generator

by leonas5555

269 downloads
Not rated
GitHub

Description

# Postman Agent Generator Welcome to your generated agent! πŸš€ This project was created with the [Postman Agent Generator](https://postman.com/explore/agent-generator), configured to [Model Context Provider (MCP)](https://modelcontextprotocol.io/introduction) Server output mode…

About

# Postman Agent Generator Welcome to your generated agent! πŸš€ This project was created with the [Postman Agent Generator](https://postman.com/explore/agent-generator), configured to [Model Context Provider (MCP)](https://modelcontextprotocol.io/introduction) Server output mode. It provides you with: - βœ… An…

Details

Author
leonas5555
Downloads
269
Categories
AI, API

- MCP-compatible server (mcpServer.js) for AI agent integration
- Automatically generated JavaScript tools for each selected Postman API request
- Environment variable support per workspace for API authentication
- Docker deployment support with included Dockerfile
- Server-Sent Events (SSE) transport option for real-time streaming
- Works with Postman Desktop and Claude Desktop clients

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Postman Agent Generator
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install dependencies with npm install, then set required environment variables in the .env file (API keys, base URLs). List available tools with node index.js tools. Run the server with node mcpServer.js (stdio) or add --sse for SSE mode. Integrate with Claude Desktop by adding the server to its config file, or use the Postman Desktop Application for easier management.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "postman agent generator": {
            "insightsentry-mcp-server": {
                "command": "node",
                "args": [
                    "index.js",
                    "tools"
                ]
            }
        }
    }
}

McpServers

{
    "insightsentry-mcp-server": {
        "command": "node",
        "args": [
            "index.js",
            "tools"
        ]
    }
}
# Postman Agent Generator Welcome to your generated agent! πŸš€ This project was created with the [Postman Agent Generator](https://postman.com/explore/agent-generator), configured to [Model Context Provider (MCP)](https://modelcontextprotocol.io/introduction) Server output mode. It provides you with: - βœ… An MCP-compatible server (`mcpServer.js`) - βœ… Automatically generated JavaScript tools for each selected Postman API request Let's set things up! ## 🚦 Getting Started ### βš™οΈ Prerequisites Before starting, please ensure you have: - [Node.js (v16+ required, v20+ recommended)](https://nodejs.org/) - [npm](https://www.npmjs.com/) (included with Node) ### πŸ“₯ Installation & Setup **1. Install dependencies** Run from your project's root directory: ```sh npm install ``` ### πŸ” Set tool environment variables In the `.env` file, you'll see environment variable placeholders, one for each workspace that the selected tools are from. For example, if you selected requests from 2 workspaces, e.g. Acme and Widgets, you'll see two placeholders: ``` ACME_API_KEY= WIDGETS_API_KEY= ``` Update the values with actual API keys for each API. These environment variables are used inside of the generated tools to set the API key for each request. You can inspect a file in the `tools` directory to see how it works. ```javascript // environment variables are used inside of each tool file const apiKey = process.env.ACME_API_KEY; ``` **Caveat:** This may not be correct for every API. The generation logic is relatively simple - for each workspace, we create an environment variable with the same name as the workspace slug, and then use that environment variable in each tool file that belongs to that workspace. If this isn't the right behavior for your chosen API, no problem! You can manually update anything in the `.env` file or tool files to accurately reflect the API's method of authentication. In the `.env` file, add the following environment variables for InsightSentry tools: ``` INSIGHTSENTRY_API_KEY=your_api_key_here INSIGHTSENTRY_BASE_URL=https://insightsentry.p.rapidapi.com INSIGHTSENTRY_WS_URL=wss://stream.insightsentry.com/quote ``` The `INSIGHTSENTRY_API_KEY` is your RapidAPI key for accessing the InsightSentry API. The `INSIGHTSENTRY_BASE_URL` is the base URL for REST API endpoints. The `INSIGHTSENTRY_WS_URL` is the WebSocket URL for real-time data streams. ### πŸ› οΈ List Available Tools List descriptions and parameters from all generated tools with: ```sh node index.js tools ``` Example: ``` Available Tools: Workspace: acme-workspace Collection: useful-api list_all_customers Description: Retrieve a list of useful things. Parameters: - magic: The required magic power - limit: Number of results returned [...additional parameters...] ``` ## 🌐 Running the MCP Server The MCP Server (`mcpServer.js`) exposes your automated API tools to MCP-compatible clients, such as Claude Desktop or the Postman Desktop Application. ### A) πŸ–₯️ Run with Postman The Postman Desktop Application is the easiest way to run and test MCP servers. Step 1: Download the latest Postman Desktop Application from [https://www.postman.com/downloads/](https://www.postman.com/downloads/). Step 2: Read out the documentation article [here](https://learning.postman.com/docs/postman-ai-agent-builder/mcp-requests/overview/) for the next steps. ### B) πŸ‘©β€πŸ’» Run with Claude Desktop To integrate with Claude Desktop: 1. Find node path: ```sh which node ``` 2. Find `mcpServer.js` path: ```sh realpath mcpServer.js ``` 3. Open Claude Desktop β†’ **Settings** β†’ **Developers** β†’ **Edit Config** and add your server: ```json { "mcpServers": { "<server_name>": { "command": "<absolute_path_to_node>", "args": ["<absolute_path_to_mcpServer.js>"] } } } ``` Restart Claude Desktop to activate this change. ### Additional Options #### 🐳 Docker Deployment (Production) For production deployments, you can use Docker: **1. Build Docker image** ```sh docker build -t <your_server_name> . ``` **2. Claude Desktop Integration** Add Docker server configuration to Claude Desktop (Settings β†’ Developers β†’ Edit Config): ```json { "mcpServers": { "<your_server_name>": { "command": "docker", "args": ["run", "-i", "--rm", "--env-file=.env", "<your_server_name>"] } } } ``` > Add your environment variables (API keys, etc.) inside the `.env` file. #### 🌐 Server-Sent Events (SSE) To run the server with Server-Sent Events (SSE) support, use the `--sse` flag: ```sh node mcpServer.js --sse ``` ## 🐳 Dockerfile (Included) The project comes bundled with the following minimal Docker setup: ```dockerfile FROM node:22.12-alpine AS builder WORKDIR /app COPY package.json package-lock.json ./ RUN npm install COPY . . ENTRYPOINT ["node", "mcpServer.js"] ``` ## βž• Adding New Tools Extend your agent with more tools easily: 1. Visit [Postman Agent Generator](https://postman.com/explore/agent-generator). 2. Pick new API request(s), generate a new agent, and download it. 3. Copy new generated tool(s) into your existing project's `tools/` folder. 4. Update your `tools/paths.js` file to include new tool references. ## πŸ’¬ Questions & Support Visit the [Postman Agent Generator](https://postman.com/explore/agent-generator) page for updates and new capabilities. Visit the [Postman Community](https://community.postman.com/) to share what you've built, ask questions and get help.
No reviews yet β€” be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.