by postmanlabs
Connects AI agents and assistants to Postman APIs, enabling natural‑language access to workspaces, collections, environments, and API specifications.
The server bridges AI tools with Postman's API ecosystem, allowing AI agents to query, modify, and automate Postman resources such as workspaces, collections, environments, and specifications through natural language commands.
https://mcp.postman.com/minimal or https://mcp.postman.com/mcp). Configure the endpoint and API key in your editor's MCP settings.npx @postman/postman-mcp-server (add --full for the full toolset). Configure your editor to launch the server as an STDIO process.https://mcp.eu.postman.com and --region flag for local server.Q: Where do I get a Postman API key? A: Generate one in the Postman web app under Settings → API Keys.
Q: What is the difference between Minimal and Full modes? A: Minimal provides the core 37 tools for basic operations; Full unlocks all 106 Postman API tools for advanced collaboration and enterprise features.
Q: How do I target the EU region?
A: Use the EU remote endpoint (https://mcp.eu.postman.com) or add --region eu (or set POSTMAN_API_BASE_URL) when launching the local server.
Q: Can I run the server inside Docker?
A: Yes. Refer to the repository's DOCKER.md for container‑based setup.
Q: How do I integrate with Claude or Gemini?
A: Install via the provided buttons or run the CLI commands shown in the README (e.g., claude mcp add --transport http postman https://mcp.postman.com/minimal).
The Postman MCP Server connects Postman to AI tools, giving AI agents and assistants the ability to access workspaces, manage collections and environments, evaluate APIs, and automate workflows through natural language interactions.
Postman supports the following tool configurations:
Designed for developers who want to integrate their AI tools with Postman’s context and features. Supports quick natural language queries queries to advanced agent workflows.
The Postman MCP Server supports the EU region for remote and local servers:
https://mcp.eu.postman.com.--region flag to specify the Postman API region (us or eu), or set the POSTMAN_API_BASE_URL environment variable directly.The remote Postman MCP Server is hosted by Postman over streamable HTTP and provides the easiest method for getting started. If your MCP host doesn't support remote MCP servers, you can use the local Postman MCP Server.
The remote server supports the following tool configurations:
https://mcp.postman.com/minimal.https://mcp.postman.com/mcp.Note: The remote EU HTTP server is available at https://mcp.eu.postman.com.
Before getting started, make certain you have a valid Postman API Key.
To install the remote Postman MCP Server in Visual Studio Code, click the install button or use the Postman VS Code Extension.
Note: By default, the server provides 37 tools. Use full mode (https://mcp.postman.com/mcp) to access all 106 tools.
To manually configure the remote Postman MCP Server in VS Code, add the following JSON block to the .vscode/mcp.json file:
{
"servers": {
"postman-api-http-server": {
"type": "http",
"url": "https://mcp.postman.com/{minimal | mcp}", // use "minimal" (default) or "mcp" (full)
"headers": {
"Authorization": "Bearer ${input:postman-api-key}"
}
}
},
"inputs": [
{
"id": "postman-api-key",
"type": "promptString",
"description": "Enter your Postman API key"
}
]
}
When prompted, enter your Postman API key. Afterwards, the agent performs calls to the Postman cloud MCP server at https://mcp.postman.com.
To install the remote Postman MCP Server in Cursor, click the install button.
Note: Ensure that the Authorization header uses the Bearer <YOUR_API_KEY> format.
To install the MCP server in Claude Code, run the following command in your terminal:
Minimal
claude mcp add --transport http postman https://mcp.postman.com/minimal
Full
claude mcp add --transport http postman https://mcp.postman.com/mcp
If remote MCP servers aren't supported by your MCP host, you can install the Postman MCP Server to your local machine.
STDIO is a lightweight solution that's ideal for integration with editors and tools like Visual Studio Code. Install an MCP-compatible VS Code extension, such as GitHub Copilot, Claude for VS Code, or other AI assistants that support MCP.
Note: For Docker set up and installation, see DOCKER.md.
The local server supports the following tool configurations:
--full flag to enable this configuration.Before getting started, you'll need the following:
To configure the extension to use the local Postman MCP Server, do the following:
npm install command. This installs all the required dependencies.${workspaceFolder} in the mcp.json file with the full path to the Postman MCP repository.To install the local Postman MCP Server in Visual Studio Code, click the install button.
Note:
--full flag to access all 106 tools.--region flag to specify the Postman API region (us or eu), or set the POSTMAN_API_BASE_URL environment variable directly. By default, the server uses the us option.You can manually integrate your MCP server with VS Code to use it with extensions that support MCP. To do this, create a .vscode/mcp.json file in your project and add the following JSON block to it:
{
"servers": {
"postman-api-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"@postman/postman-mcp-server",
"--full" // (optional) Use this flag to enable full mode
],
"env": {
"POSTMAN_API_KEY": "${input:postman-api-key}"
}
}
},
"inputs": [
{
"id": "postman-api-key",
"type": "promptString",
"description": "Enter your Postman API key"
}
]
}
To install the local Postman MCP Server in Cursor, click the install button.
To integrate the MCP server with Claude, check the latest Postman MCP Server release and get the .mcpb file.
postman-api-mcp-minimal.mcpb - Contains the 37 essential tools for common Postman operations.postman-api-mcp-full.mcpb - Contains all available Postman tools.For more information, see Anthropic's Claude Desktop Extensions documentation.
To install the MCP server in Claude Code, run the following command in your terminal:
Minimal
claude mcp add postman -- npx @postman/mcp-server@latest
Full
claude mcp add postman -- npx @postman/mcp-server@latest --full
To install the MCP server as a Gemini CLI extension, run the following command in your terminal:
gemini extensions install https://github.com/postmanlabs/postman-mcp-server
If you're migrating from Postman MCP Server version 1.x to 2.x, be aware of the following:
create-collection → createCollectionget-workspaces → getWorkspacesdelete-environment → deleteEnvironment--full flag provides access to all 106 tools.Please log in to share your review and rating for this MCP.
{
"mcpServers": {
"postman-mcp": {
"command": "npx",
"args": [
"@postman/postman-mcp-server"
],
"env": {
"POSTMAN_API_KEY": "<YOUR_API_KEY>"
}
}
}
}claude mcp add postman-mcp npx @postman/postman-mcp-serverExplore related MCPs that share similar capabilities and solve comparable challenges
by zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
by modelcontextprotocol
Model Context Protocol Servers
by modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
by modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
by cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
by continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
by upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.