postman-mcp
A Model Context Protocol (MCP) server that provides seamless integration with the Postman API, enabling AI assistants and applications to interact with Postman workspaces, collections, requests, environments, and folders programmatically.
README
Postman MCP
A Model Context Protocol (MCP) server that provides seamless integration with the Postman API. This package enables AI assistants and applications to interact with Postman workspaces, collections, requests, environments, and folders programmatically.
🚀 Features
📁 Workspace Management
- List all workspaces
- Get detailed workspace information
- Create new workspaces (personal/team)
- Update workspace metadata
📚 Collection Management
- List collections within workspaces
- Get collection details with full structure
- Create new collections
- Update collection metadata and variables
- Delete collections
🔧 Request Management
- Add new HTTP requests to collections
- Update existing requests (method, URL, headers, body)
- Move requests between folders
- Delete requests
- Support for all HTTP methods (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS)
🌍 Environment Management
- List environments in workspaces
- Get environment details and variables
- Create new environments with variables
- Update environment variables
- Delete environments
- Support for secret, default, and custom variable types
📂 Folder Organization
- Create nested folder structures
- Organize requests within folders
- Support for hierarchical folder paths
⚙️ Setup
1. Get Your Postman API Key
- Go to Postman Account Settings
- Click "Generate API Key"
- Give it a name and copy the generated key
2. MCP Configuration
For Claude Desktop
Add to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"postman": {
"command": "npx",
"args": ["postman-mcp"],
"env": {
"POSTMAN_API_KEY": "your_postman_api_key_here"
}
}
}
}
For Cursor
Add the configuration to your Cursor settings:
{
"mcp": {
"servers": {
"postman": {
"command": "npx postman-mcp",
"env": {
"POSTMAN_API_KEY": "your_postman_api_key_here"
}
}
}
}
}
For Warp
Add the following to your Warp session setup:
{
"postman": {
"command": "npx",
"args": ["postman-mcp"],
"env": {
"POSTMAN_API_KEY": "your_postman_api_key_here"
},
"working_directory": null,
"start_on_launch": true
}
}
For Other MCP Clients
Use the standard MCP server connection with:
- Command:
npx postman-mcpornode path/to/postman-mcp/dist/index.js - Transport: stdio
- Environment: Set
POSTMAN_API_KEY
🛠️ Development Setup
Prerequisites
- Node.js 18+
- npm or yarn
- Postman API key
Local Development
-
Clone the repository:
git clone https://github.com/SalehKhatri/postman-mcp.git cd postman-mcp -
Install dependencies:
npm install -
Set up environment:
cp .env.example .env # Edit .env and add your POSTMAN_API_KEY -
Build the project:
npm run build -
Run in development mode:
npm run dev
🔍 Available Tools
Workspace Operations
list_workspaces- Get all workspacesget_workspace- Get workspace detailscreate_workspace- Create new workspaceupdate_workspace- Update workspace info
Collection Operations
list_collections- Get collections in workspaceget_collection- Get full collection structurecreate_collection- Create new collectionupdate_collection- Update collection metadatadelete_collection- Remove collection
Request Operations
add_request- Add HTTP request to collectionupdate_request- Modify existing requestdelete_request- Remove request from collection
Environment Operations
list_environments- Get environments in workspaceget_environment- Get environment variablescreate_environment- Create new environmentupdate_environment- Modify environment variablesdelete_environment- Remove environment
Folder Operations
create_folder- Create folder in collection
💡 Usage Examples
Basic Workflow
// List all workspaces
const workspaces = await mcp.callTool("list_workspaces", {});
// Get collections in a workspace
const collections = await mcp.callTool("list_collections", {
workspaceId: "workspace-id",
});
// Create a new request
await mcp.callTool("add_request", {
collectionUid: "collection-uid",
name: "Get Users",
method: "GET",
url: "https://api.example.com/users",
headers: {
"Content-Type": "application/json",
Authorization: "Bearer {{token}}",
},
folder: "API/Users",
});
// Create an environment
await mcp.callTool("create_environment", {
name: "Production",
workspaceId: "workspace-id",
values: [
{
key: "base_url",
value: "https://api.production.com",
type: "default",
},
{
key: "api_key",
value: "secret-key",
type: "secret",
},
],
});
🔐 Security
- API Key Protection: Store your Postman API key securely using environment variables
- Scope Limitation: The API key should have minimal required permissions
- Network Security: All requests use HTTPS to communicate with Postman API
🤝 Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🔗 Links
📞 Support
- Create an issue for bug reports or feature requests
- Check existing issues before creating new ones
- Provide detailed information including error messages and environment details
Made with ❤️ for the developer community
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。