home / mcp / postman mcp server
Expose the [Postman API](https://api.getpostman.com) as a set of [Model‑Context Protocol (MCP)] tools. This project wraps core Postman API endpoints into well‑typed tools that can be invoked by your favourite MCP host
Configuration
View docs{
"mcpServers": {
"anarsyakir-postman-mcp": {
"command": "docker",
"args": [
"compose",
"run",
"-e",
"POSTMAN_API_KEY=YOUR_API_KEY",
"postman-mcp"
],
"env": {
"POSTMAN_API_KEY": "pmak-xxxxxxxxxxxxxxxxxxxx",
"POSTMAN_BASE_URL": "https://api.getpostman.com",
"DEFAULT_WORKSPACE_ID": "<DEFAULT_WORKSPACE_ID>"
}
}
}
}You expose the Postman API as a set of MCP tools that you can call from your MCP host. This server wraps core Postman endpoints into well‑typed commands so you can list workspaces, manage collections and requests, create responses, and run monitors directly from chat or code.
You connect to this MCP server from your MCP client (for example, Codex or Claude Desktop) and invoke tools by name. Use the tools to navigate Postman data: list workspaces, fetch workspace details, inspect and modify collections, add requests, create responses, and run monitors. Each tool corresponds to a Postman API operation and returns structured results you can use in your workflow.
Prerequisites: you need Node.js installed on your machine and a running MCP host to connect with. Ensure you have an API key from Postman and, optionally, a default workspace to target.
Option 1: Local development install and run
Step 1: Install dependencies for the MCP server locally.
Step 2: Create a local environment file and set your Postman API key and base URL.
Step 3: Start the server in development mode.
Configure your MCP host to connect to this server using the provided runtime commands. You can run the server in development mode or via container tooling as shown in the examples. The following options are available to run the MCP server locally or in Docker.
Environment variables you provide control authentication and endpoint behavior. Common variables include the Postman API key, the base API URL, and an optional default workspace.
List all workspaces you can access with your API key.
Protect your Postman API key. Do not share your environment file or command history that includes the key. Use separate keys for different environments or teams as needed.
If a tool call fails, verify your API key is valid and that the key has access to the requested workspace or collection. Check that the base URL is correct and reachable from your environment.
List every workspace accessible with the authenticated API key using GET /workspaces.
Fetch details of a single workspace by ID, including its collections, environments, mocks and monitors.
Return the collection references contained in a workspace by its ID, extracting the collections array from the workspace data.
Create a new collection from a Postman Collection v2 object; can save into a specific workspace via an optional workspaceId parameter.
Retrieve a complete collection definition by its UID using GET /collections/{collectionUid}.
Replace an existing collection with a new Collection v2 payload via PUT /collections/{collectionUid}.
Add a new request to a collection by posting a request object to POST /collections/{collectionId}/requests.
Fetch a single request item from a collection with GET /collections/{collectionId}/requests/{requestId}.
Replace an existing request using PUT /collections/{collectionId}/requests/{requestId}.
Create a sample response for a request via POST /collections/{collectionId}/responses?request={requestId}.
Get a response example by ID using GET /collections/{collectionId}/responses/{responseId}.
Update an existing response example via PUT /collections/{collectionId}/responses/{responseId}.
Execute a monitor synchronously via POST /monitors/{monitorUid}/run and return the run results.