Integration · Company data

Connect Claude & ChatGPT to Apify

Ask your AI to run a scraper from the Apify Store, rerun one of your saved tasks or pull the results of the last run. It can search the Store for Actors, start runs with a cost cap, read datasets, key-value store records and run logs, and tell you how much of this billing cycle's usage is left.

Connect Apify free

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

Try asking

“Find an Actor in the Apify Store that scrapes Google Maps.”
The AI searches the public Apify Store and lists matching Actors, so you can pick one and read its details.
“Run my competitor-prices task and show me the results.”
It runs the saved task, waits for it to finish (up to 5 minutes) and returns the result items.
“Why did yesterday's run fail?”
It lists runs with status FAILED, then reads the run's log so you can see the error.

What your AI can do

Actors and tasks

Search the Apify Store, read Actor details, start Actors and saved tasks, create tasks and replace their saved input.

Runs and results

List and read runs, abort a running run, read run logs and fetch the result items when a run is done.

Storage and usage

Read datasets and key-value store records, and check account limits and monthly usage and costs.

“Run this Actor on these five URLs, but spend at most 2 USD.”
It starts the run with your URLs as input and max_total_charge_usd set to 2, so the cost is capped.
“How much of our usage have we spent this month?”
It reads your account limits and usage for the billing cycle, including compute units and the monthly spend cap.
“Give me only the title and price fields from my latest dataset.”
It lists your datasets and fetches the items, trimmed to the fields you asked for.

29 tools for Apify

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

abort_runChanges dataStop a running Actor run by `run_id`; set `gracefully` to let it finish its current work first.
create_taskChanges dataSave a new task for an Actor (`act_id`) with a `name` and `input`, so it can be re-run later with the same settings.
get_account_limitsGet the account's usage limits and how much of them is used this billing cycle (compute units, monthly spend cap).
get_actorGet one Actor by `actor_id` (an ID or username~actor-name), including its description, versions and default run settings.
get_current_userGet the connected Apify account's own profile and plan. Use to confirm which account you are working in.
get_datasetGet a dataset's details (name, item count, dates) by `dataset_id`.
get_dataset_itemsGet the items stored in a dataset by `dataset_id`. Use `limit`, `offset` and `fields` to page and trim the output.
get_last_task_resultsGet the result items of a task's most recent run (`actor_task_id`); filter with `status`=SUCCEEDED to skip failed runs.
get_monthly_usageGet the account's usage and costs for a billing month; optional `date` (YYYY-MM-DD) picks the month.
get_runGet one run by `run_id`: status, start/finish time, cost and the IDs of its default dataset and key-value store.
get_run_logGet the log text of a run by `run_id`, useful to see why a run failed.
get_run_resultsGet the result items a run produced (its default dataset) by `run_id`. Use `limit`, `offset`, `fields` or `clean` to trim the output.
get_store_recordGet one record (e.g. OUTPUT, a screenshot or JSON file) from a key-value store by `store_id` and `record_key`.
get_taskGet one saved task by `task_id`, including which Actor it runs and its options.
get_task_inputGet the saved input of a task (`actor_task_id`).
list_actor_runsList the runs of one Actor (`actor_id`), optionally filtered by `status` or start date.
list_actorsList Actors in your account; set `my` to true to show only Actors you created.
list_datasetsList your datasets (stored result tables), newest last unless `desc` is true.
list_key_value_storesList your key-value stores (where Actors save files and records).
list_runsList all Actor runs in the account, newest last unless `desc` is true; filter by `status` (e.g. SUCCEEDED, FAILED, RUNNING) or start date.
list_store_keysList the record keys in a key-value store (`store_id`).
list_task_runsList the runs of a saved task (`actor_task_id`), optionally filtered by `status`.
list_tasksList your saved Actor tasks (an Actor with pre-set input).
run_actorChanges dataStart a run of an Actor (`actor_id`) with its input as `body`. Returns the run right away (or waits up to `wait_for_finish` seconds). Runs use paid platform credits; set `max_total_charge_usd` to cap the cost.
run_actor_and_get_resultsChanges dataRun an Actor (`actor_id`) with input `body`, wait for it to finish (up to 5 minutes) and return its dataset items. Uses paid platform credits; set `max_items` or `max_total_charge_usd` to cap cost.
run_taskChanges dataStart a run of a saved task (`actor_task_id`); `body` optionally overrides parts of its input. Runs use paid platform credits; set `max_total_charge_usd` to cap the cost.
run_task_and_get_resultsChanges dataRun a saved task (`actor_task_id`), wait for it to finish (up to 5 minutes) and return its dataset items. Uses paid platform credits.
search_store_actorsSearch the public Apify Store for ready-made Actors (scrapers, automations) by `search` text, `category`, `username` or `pricing_model`.
update_task_inputVisible to othersReplace the saved input of a task (`actor_task_id`) with `body`.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Apify from the app list.
2
Paste your key
Paste your Apify API token. In Apify Console, open Settings > API & Integrations and copy your personal API token, or create a new token with limited scope.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
Click your name, then Settings › Connectors › Add custom connector. Paste your link as the Remote MCP server URL. Switch it on from the + menu in a chat.

Questions

What can the AI do in Apify?

The AI can search the Apify Store and read your Actors, tasks, runs, run logs, datasets and key-value stores, plus your account limits and monthly usage. It can start Actors and saved tasks, wait for their results, abort runs, create tasks and replace a task's saved input.

Does the AI see my Apify API token?

No. Your Apify API token is encrypted at rest and never shown to the AI. After you save it, it is 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 with only reading runs and datasets. Starting a run uses paid Apify platform credits, so the run tools can require your approval before they run, and you can cap the cost of a run with max_total_charge_usd. 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 Apify account, and Actor runs use your Apify platform credits, which is between you and Apify.

What is the difference between an Actor and a task?

An Actor is a program on Apify, such as a scraper. A task is an Actor saved with fixed input, so you can run it again with the same settings. The AI can run either one, and it can save a new task for an Actor you use often.