Arlet
Postman

Connect Postman to ChatGPT

Search, read and write Postman from ChatGPT. Arlet links the two through one MCP connection and takes care of keys and authentication.

Enable Postman in ArletChatGPT connection guide (docs)

Arlet makes Postman's official MCP server available from the AI client you already use. Signing in completes the connection.

The AI can work with workspaces and collections, add and update requests, manage environments, specs and mocks, and run collections. This uses the US region's Minimal configuration (about 40 core tools); the available tools are those provided by Postman's official server.

How to connect Postman to ChatGPT

  1. 1

    In the Arlet dashboard, open Integrations → Add an integration and choose Postman. Sign in with Link Postman, name the connection and click Create.

  2. 2

    In ChatGPT, open Settings → Plugins → Browse plugins and click + at the top right.

  3. 3

    In the New Plugin form, enter "Arlet" as the Name, choose Server URL for Connection and enter https://mcp.arlet.dev/mcp/, pick OAuth for Authentication, check the risk acknowledgement and click Create.

  4. 4

    Open the Arlet plugin you created, click Sign in with Arlet, sign in with Google and click Allow. The connection is complete.

If the Plugins screen is not shown, turn on Developer mode under Settings → Security and login.

What you can do

Postman tools that ChatGPT can call.

  • getWorkspaces

    List workspaces.

  • getCollections

    List the collections in a workspace.

  • getCollection

    Get a collection's structure.

  • createCollection

    Create a collection.

  • createCollectionRequest

    Add a request to a collection.

  • updateCollectionRequest

    Update a request.

  • runCollection

    Run a collection and return the results.

  • getEnvironments

    List environments.

  • createEnvironment

    Create an environment.

  • getAllSpecs

    List API specs.

  • createSpec

    Create an API spec.

  • generateCollection

    Generate a collection from a spec.

  • syncCollectionWithSpec

    Sync a collection with its spec.

  • createMock

    Create a mock server.

  • searchPostmanElements

    Search elements in a workspace.

The tool list follows what Postman's official MCP server provides and may change.

Example uses

  • Run API tests

    Run a collection and summarize failing requests and why.

  • Build a collection from a spec

    Register an OpenAPI spec, generate a collection and set up an environment.

  • Maintain requests

    Add requests for new endpoints to an existing collection with examples and tests.

  • Develop against a mock

    Create a mock server from a spec so front-end work can start early.

Prompts you can use as-is

  • Run the Payments API collection against the staging environment and summarize the failures
  • Register this OpenAPI spec and create a collection and a staging environment for it
  • Add a POST /refunds request to the Payments API collection
  • Create a mock server from the Payments API spec and give me the URL

Use Postman with other AI clients