# Your Apify Actors. Run from your agent.

Source: https://corespeed.io/integrations/apify

Connect Apify to Claude Code, Codex, Cursor or any MCP agent through CoreSpeed. Your agent searches the Apify Store for an Actor, runs it, follows the run and its log, and reads the dataset it produces. It signs in with your own Apify account, and running an Actor is a separate call that approvals can hold.

## Set up an agent

Give your agent this line: `set up https://corespeed.io/SKILL.md (read it raw, e.g. with curl)`

It fetches the skill at https://corespeed.io/SKILL.md, adds the CoreSpeed MCP server, signs you in (or up), and keeps the skill for next time. Connect Apify after setup. Access follows the connected account and its permissions. Create an account: https://app.corespeed.io/sign-up

## One Actor. One clear answer

Have your agent pick an Actor from the Apify Store, run it with the limits you set, and turn its dataset into a short brief.

You ask your agent: "Find an Apify Actor that collects public app reviews. Run it on our app with a limit of 200 reviews, then summarize the most common complaints."

It calls CoreSpeed:

- `apify__search-actors`: ok, 512 ms
- `apify__call-actor`: ok, 48210 ms
- `apify__get-dataset-items`: ok, 690 ms

It reads from: Apify.

### Review digest: What reviewers ask for.

Slow sync on large files is the most common complaint. The offline mode is the most praised feature.

**Top complaints**

- Sync is slow on large files.
- Search misses older notes.

**Worth keeping**

- The offline mode.
- Fast start on a new phone.

_Illustrative run and reviews · 200 items read from one dataset_

All connectors: https://corespeed.io/docs/connectors

## Pick the Actor. Keep the data

Requests you can make once Apify is connected. The data is fictional.

### Find the right Actor

Actors for public app reviews · Store search

- Best fit: App review collector
- Why: Takes an app URL and a review limit
- A shortlist · Nothing run yet

### Ask before a large run

A run that waits for you · Approvals

- Actor: App review collector
- Limit: 5,000 reviews
- Held for a person

### Read what a run collected

Dataset · 200 reviews · Dataset items

- Most common: Sync is slow on large files
- Most praised: The offline mode
- Read from the dataset · Nothing changed

## Keep your agent. Bring your work

One CoreSpeed account, across compatible agents.

1. **Set up CoreSpeed**: Give your agent the setup line. It adds CoreSpeed and signs you in.
2. **Connect Apify**: Authorize the account and the content you need.
3. **Start with one task**: Ask for a summary, a brief, or a draft. Review the answer.

Setup guides: Claude Code https://corespeed.io/docs/mcp#claude-code · Codex https://corespeed.io/docs/mcp#codex · Cursor https://corespeed.io/docs/mcp#cursor

## Questions

### Whose Apify credits does a run use?

Yours. Your agent runs Actors on your own Apify account, so each run spends that account’s credits, as it would in the Apify console.

### Can my agent run any Actor?

It can run the Actors your Apify account can run. Each run is a separate tool call, which approvals can hold for a person. How approvals work: https://corespeed.io/docs/approvals

### Do I paste an Apify token into each agent?

No. You sign in to Apify once through CoreSpeed. Every agent you set up with CoreSpeed then uses that connection.

### Do I have to switch agents?

No. CoreSpeed adds tools to the agent you already use: Claude Code, Codex, Cursor, or another MCP client. Each one signs in once.

### Can my agent access every account in our organization?

No. Access follows your CoreSpeed identity, each connection's visibility, and the app's own permissions. Personal connections stay private.

### Does this work without connecting an account?

No. Connect the app's account first; your CoreSpeed workspace shows what each app needs. The examples on this page use fictional data. All connectors: https://corespeed.io/docs/connectors

Every tool and price: https://corespeed.io/catalog/apify

## Related pages

- [Firecrawl for Claude Code, Codex, and Cursor](https://corespeed.io/integrations/firecrawl): Turn web pages, whole sites and PDFs into clean Markdown your agent can read, with your own Firecrawl key.
- [MCP gateway for your agents and tools](https://corespeed.io/solutions/mcp-gateway): Reach connected apps, built-in tools, and your own remote MCP servers through one authenticated CoreSpeed MCP endpoint.
- [TinyFish for Claude Code, Codex, and Cursor](https://corespeed.io/integrations/tinyfish): Send a TinyFish web agent to a real site with a plain-language goal, and get structured results back in your agent.

## Sources

- Connectors: https://corespeed.io/docs/connectors
- Apify Actors: https://docs.apify.com/platform/actors
- Apify datasets: https://docs.apify.com/platform/storage/dataset
- Apify MCP server: https://docs.apify.com/platform/integrations/mcp

Reviewed 2026-11-10.

## Links

- Product overview: https://corespeed.io/ (Markdown: https://corespeed.io/index.md)
- All integrations: https://corespeed.io/integrations (Markdown: https://corespeed.io/integrations.md)
- Documentation: https://corespeed.io/docs
- Pricing: https://corespeed.io/pricing (Markdown: https://corespeed.io/pricing.md)