Integration · Developer tools

Connect Claude & ChatGPT to Postman

Ask your AI what is in your Postman workspaces and have it do the edits. It can read collections, folders, requests, saved responses, environments, mock servers, monitors and API specs. It can also create collections, folders, requests and environments, update requests, comment on a collection and run a monitor on demand.

Connect Postman free

Free plan, no credit card. Takes about a minute.

Try asking

“Which collections are in our Payments workspace?”
The AI gets the workspace and lists its collections, environments, mocks and monitors.
“Add a GET request for /v1/orders to the Orders API collection.”
It creates the request with name, method, URL, headers and query parameters, in the folder you name.
“Change the base URL on the Create order request to staging.”
It updates only the URL on that request and leaves the rest as it is.

What your AI can do

Workspaces and collections

List workspaces and collections, and read full collections with folders, requests, saved responses and variables.

Build and edit requests

Create collections, folders, requests and environments, and update requests, folders and collection details.

Monitors, mocks and specs

List and read monitors, mock servers and API specs, run a monitor now, and read or add collection comments.

“Set up a Staging environment with base_url and api_version.”
It creates the environment in the workspace with the variables you give it.
“Run the nightly health check monitor now.”
It runs the monitor, which sends the collection's requests to the real APIs, and shows the run results.
“Leave a comment on the collection that the auth folder is out of date.”
It adds the comment to the collection, where others with access can see it.

27 tools for Postman

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_collection_commentChanges dataComment on a collection by its unique ID (`collection_id`) with the comment `body`. Pass `thread_id` to reply in an existing thread. Other users with access can see the comment.
create_collectionChanges dataCreate a collection in a `workspace`. Pass `collection` with `info` (at least a name) and `item` (the list of folders and requests, which can be empty).
create_environmentChanges dataCreate an environment in a `workspace`. Pass `environment` with a `name` and optional `values` (its variables).
create_folderChanges dataCreate a folder in a collection (`collection_id`) with a `name`. Pass `folder` to nest it inside another folder.
create_requestChanges dataAdd a request to a collection (`collection_id`) with `name`, `method`, `url`, `header_data`, `query_params` and a body (`raw_mode_data`). Pass `folder_id` to place it in a folder.
delete_requestDeletesPermanently delete a request from a collection by `collection_id` and the request's ID (`category_id`).
get_collectionGet a full collection (folders, requests, variables) by its collection ID (`category_id`). Set `model` to minimal to get only the top-level folder and request IDs.
get_environmentGet an environment and its variables by `environment_id`.
get_folderGet a folder by `collection_id` and the folder's ID (`category_id`).
get_meGet the Postman user the API key belongs to, including user ID and team.
get_mockGet a mock server by `mock_id`, including its URL and the collection it serves.
get_monitorGet a monitor by `monitor_id`, including its schedule and last run results.
get_requestGet a request from a collection by `collection_id` and the request's ID (`category_id`).
get_saved_responseGet a saved example response by `collection_id` and the response's ID (`category_id`).
get_specGet an API specification by its ID (`property_id`).
get_workspaceGet a workspace by `workspace_id`, including the collections, environments, mocks and monitors in it.
list_collection_commentsList the comments on a collection by its unique ID (`collection_id`, in userId-collectionId form).
list_collectionsList collections, optionally in one `workspace` or matching an exact `name`.
list_environmentsList environments, optionally in one `workspace`.
list_mocksList mock servers, optionally in one `workspace`.
list_monitorsList monitors (scheduled collection runs). Optional filters: `workspace`, `collection_uid`, `environment_uid` and `active`.
list_specsList the API specifications in a workspace by `workspace_id`.
list_workspacesList the workspaces you can access, optionally filtered by `type` (personal, team, private, public, partner).
run_monitorChanges dataRun a monitor now by `monitor_id`. The collection's requests are sent to the real APIs, and the run results are returned.
update_collectionChanges dataUpdate a collection by its ID (`category_id`). Only the parts you pass in `collection` change: `info` (name, description), `variable`, `auth` or `events`.
update_folderChanges dataRename a folder or change its description, by `collection_id` and the folder's ID (`category_id`).
update_requestChanges dataUpdate a request by `collection_id` and the request's ID (`category_id`), for example its `name`, `method`, `url`, headers or body. Only the fields you pass change.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Postman from the app list.
2
Paste your key
Paste your Postman API key. In Postman click the settings icon in the header and choose Settings > Account settings, open API keys and click Generate API Key. Name it, generate it and copy the key.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Postman?

The AI can list and read workspaces, collections, folders, requests, saved responses, environments, mock servers, monitors, API specs and collection comments. It can create collections, folders, requests and environments, update collections, folders and requests, comment on a collection, run a monitor and delete a request if you switch that tool on.

Does the AI see my Postman API key?

No. Your Postman credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start read-only. Deleting a request is permanent, and running a monitor sends real API calls, so both can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Postman account.

Can the AI run my API tests?

It can run a Postman monitor on demand. The monitor sends its collection's requests to the real APIs, and the AI gets the run results back. It does not send requests from a collection on its own outside a monitor.