This project is part of the Model Context Protocol (MCP) initiative from Anthropic. For more information, visit the MCP GitHub repository and the announcement on the Anthropic blog.
[Skip ahead to install instructions](#installation)
postman-mcp-server - Cover Image
[!WARNING]
This project is currently under active development. Please use with caution and expect breaking changes.
[!NOTE]
AI Generated Code. I used Cline v2.2.2 with Claude 3.5 Sonnet (2024-10-22). See docs/README.md for prompts and details about how this code was generated.
Postman MCP Server is a TypeScript-based MCP server that integrates with the Postman API, providing comprehensive management of Postman collections, environments, and APIs.
Features
Collections
CRUD Operations: Create, retrieve, update, and delete Postman collections.
Folder Management: Organize requests into folders within collections.
Request Management: Add, update, and delete requests within collections.
Response Management: Manage responses associated with requests.
Version Control: Fork, merge, and pull changes for collections.
Comments: Add and manage comments on collections.
Environments
Manage Environments: Create and retrieve environments for different setups.
CRUD Operations: Full support for creating, updating, and deleting environments.
APIs
API Management: Create, retrieve, update, and delete APIs.
Schema Support: Manage API schemas with multi-file support.
Tagging: Add and manage tags for APIs.
Comments: Add and manage comments on APIs.
Authentication & Authorization
API Key Authentication: Secure access using API keys.
Role-Based Access Control: Manage permissions at workspace and collection levels.
Workspace Permissions: Define permissions specific to workspaces.
Additional Features
Private API Network: Manage elements and folders within a private API network.
Webhooks: Create webhooks to trigger collections with custom payloads.
Enterprise Features: Advanced role controls and SCIM support for enterprise environments.
Installation
Installing via Smithery
To install Postman MCP Server for Claude Desktop automatically via Smithery:
[!IMPORTANT]
If you're updating this provider, Claude must be restarted to pick up API changes from the input schema (i.e. When the MCP server's ToolDefinition elements have changed). This is because Claude caches the tool definitions when it starts up.
Example configuration
Using Cline
Using the same example configuration, add the server config to your Cline MCP Servers configuration:
Example configuration
Same as Claude above.
Using Zed
I'm still trying to get this to work. From the Zed docs it looks like it needs to be an extension (also this issue #21455).
This project leverages the Claude model and Cline extension to convert the OpenAPI specification into TypeScript code, enhancing type safety and integration within the MCP server.
This GitHub project includes API References documentation that provides detailed guidance on utilizing the Postman platform programmatically. It covers both the Collection SDK for local development and the Postman API for cloud platform integration. Key topics include authentication mechanisms, rate limits, and in-depth documentation of all API endpoints, including workspaces, collections, environments, mock servers, monitors, and more. Additionally, the guide offers prerequisites and quick-start instructions to facilitate seamless API interactions.
The docs/api/summaries directory contains comprehensive Markdown summaries of the Postman API. These documents outline API endpoints, request/response formats, and implementation details essential for validating and ensuring the functionality of the MCP server. Refer to the API Summaries README for an overview of the documentation structure and implementation strategies.
Converting OpenAPI Spec to TypeScript Code with Claude
Building the MCP Server
Refer to the Handlers Documentation for detailed specifications on implementing MCP server handlers. This includes URI formats, prompt requirements, and resource handling patterns. This guide is crucial for developers working on integrating and enhancing the Postman API functionalities within the MCP server.
Rationale
The MCP wrapper for Postman tools makes sense primarily as an AI interaction layer for complex, multi-step operations where structure and safety are paramount. However, it may be overengineered for simple operations where direct CLI or API usage would suffice. The MCP wrapper provides most value when:
Complex Operations
Managing multiple collections
Coordinating environments
Generating comprehensive reports
AI-Driven Automation
Automated testing workflows
API documentation maintenance
Environment management
Error-Sensitive Operations
Critical API testing
Production deployments
Compliance checking
It provides less value for:
Simple Operations
Basic collection runs
Single API calls
Quick environment checks
Direct CLI Usage
Developer-driven operations
Local testing
Quick iterations
Development
Install dependencies:
Build the server:
For development with auto-rebuild:
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, available as a package script:
The Inspector will provide a URL to access debugging tools in your browser: http://localhost:5173. You will need to add the POSTMAN_API_KEY before connecting. Navigate to "Tools" to get started.
This project is part of the Model Context Protocol (MCP) initiative from Anthropic. For more information, visit the MCP GitHub repository and the announcement on the Anthropic blog.
[Skip ahead to install instructions](#installation)
postman-mcp-server - Cover Image
[!WARNING]
This project is currently under active development. Please use with caution and expect breaking changes.
[!NOTE]
AI Generated Code. I used Cline v2.2.2 with Claude 3.5 Sonnet (2024-10-22). See docs/README.md for prompts and details about how this code was generated.
Postman MCP Server is a TypeScript-based MCP server that integrates with the Postman API, providing comprehensive management of Postman collections, environments, and APIs.
Features
Collections
CRUD Operations: Create, retrieve, update, and delete Postman collections.
Folder Management: Organize requests into folders within collections.
Request Management: Add, update, and delete requests within collections.
Response Management: Manage responses associated with requests.
Version Control: Fork, merge, and pull changes for collections.
Comments: Add and manage comments on collections.
Environments
Manage Environments: Create and retrieve environments for different setups.
CRUD Operations: Full support for creating, updating, and deleting environments.
APIs
API Management: Create, retrieve, update, and delete APIs.
Schema Support: Manage API schemas with multi-file support.
Tagging: Add and manage tags for APIs.
Comments: Add and manage comments on APIs.
Authentication & Authorization
API Key Authentication: Secure access using API keys.
Role-Based Access Control: Manage permissions at workspace and collection levels.
Workspace Permissions: Define permissions specific to workspaces.
Additional Features
Private API Network: Manage elements and folders within a private API network.
Webhooks: Create webhooks to trigger collections with custom payloads.
Enterprise Features: Advanced role controls and SCIM support for enterprise environments.
Installation
Installing via Smithery
To install Postman MCP Server for Claude Desktop automatically via Smithery:
[!IMPORTANT]
If you're updating this provider, Claude must be restarted to pick up API changes from the input schema (i.e. When the MCP server's ToolDefinition elements have changed). This is because Claude caches the tool definitions when it starts up.
Example configuration
Using Cline
Using the same example configuration, add the server config to your Cline MCP Servers configuration:
Example configuration
Same as Claude above.
Using Zed
I'm still trying to get this to work. From the Zed docs it looks like it needs to be an extension (also this issue #21455).
This project leverages the Claude model and Cline extension to convert the OpenAPI specification into TypeScript code, enhancing type safety and integration within the MCP server.
This GitHub project includes API References documentation that provides detailed guidance on utilizing the Postman platform programmatically. It covers both the Collection SDK for local development and the Postman API for cloud platform integration. Key topics include authentication mechanisms, rate limits, and in-depth documentation of all API endpoints, including workspaces, collections, environments, mock servers, monitors, and more. Additionally, the guide offers prerequisites and quick-start instructions to facilitate seamless API interactions.
The docs/api/summaries directory contains comprehensive Markdown summaries of the Postman API. These documents outline API endpoints, request/response formats, and implementation details essential for validating and ensuring the functionality of the MCP server. Refer to the API Summaries README for an overview of the documentation structure and implementation strategies.
Converting OpenAPI Spec to TypeScript Code with Claude
Building the MCP Server
Refer to the Handlers Documentation for detailed specifications on implementing MCP server handlers. This includes URI formats, prompt requirements, and resource handling patterns. This guide is crucial for developers working on integrating and enhancing the Postman API functionalities within the MCP server.
Rationale
The MCP wrapper for Postman tools makes sense primarily as an AI interaction layer for complex, multi-step operations where structure and safety are paramount. However, it may be overengineered for simple operations where direct CLI or API usage would suffice. The MCP wrapper provides most value when:
Complex Operations
Managing multiple collections
Coordinating environments
Generating comprehensive reports
AI-Driven Automation
Automated testing workflows
API documentation maintenance
Environment management
Error-Sensitive Operations
Critical API testing
Production deployments
Compliance checking
It provides less value for:
Simple Operations
Basic collection runs
Single API calls
Quick environment checks
Direct CLI Usage
Developer-driven operations
Local testing
Quick iterations
Development
Install dependencies:
Build the server:
For development with auto-rebuild:
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, available as a package script:
The Inspector will provide a URL to access debugging tools in your browser: http://localhost:5173. You will need to add the POSTMAN_API_KEY before connecting. Navigate to "Tools" to get started.