What your AI apps can do with Apify
- Find and run Actors
- Read datasets and results
Apify MCP tools
27 tools, taken from the publisher's documentation on 29 October 2026. The server decides what it offers and can add or rename tools at any time; after you connect, Toolstile shows the current list.
| Tool | What it does |
|---|---|
search-actors | Searches for Actors in Apify Store |
fetch-actor-details | Gets an Actor's input/output schema, README and pricing |
call-actor | Starts an Actor run and returns its status and storage IDs |
search-apify-docs | Searches the Apify documentation |
fetch-apify-docs | Gets the full text of an Apify docs page |
get-actor-run | Gets details of an Actor run |
get-actor-run-list | Lists an Actor's runs, filterable by status |
get-actor-run-log | Gets the log of an Actor run |
abort-actor-run | Aborts a running Actor run |
get-dataset | Gets dataset metadata |
get-dataset-items | Gets dataset items with filtering and pagination |
get-dataset-schema | Generates a JSON schema from dataset items |
get-key-value-store | Gets key-value store metadata |
get-key-value-store-keys | Lists the keys in a key-value store |
get-key-value-store-record | Gets the value of a key-value store record |
get-dataset-list | Lists your datasets |
get-key-value-store-list | Lists your key-value stores |
get-actor-task | Gets a saved Actor task and its publication settings |
create-actor-task | Creates a named, reusable Actor task configuration |
update-actor-task | Updates an Actor task's input, run options or display settings |
publish-actor-task | Publishes an Actor task to its public landing page |
unpublish-actor-task | Removes an Actor task from its public landing page |
create-schedule | Creates a cron schedule for Actors or tasks |
get-schedule | Gets a schedule's cron, time zone, state and next run |
update-schedule | Updates a schedule's cron, time zone, state or actions |
delete-schedule | Permanently deletes a schedule |
report-problem | Reports a problem with the MCP server to Apify |
Suggested access for each AI app
The documentation this list comes from doesn't mark Apify's tools as read-only or destructive. Read each tool's description and decide per app before allowing it.
Coding agent in Claude Code or Cursor. Allow the read tools so the agent can look things up without stopping, and require approval for tools that change shared data.
Chat or research app in Claude Desktop. Allow reading and searching. Allow writes only where you want the app to act for you.
Unattended agent, such as a scheduled Codex job. No one is watching the session, so keep it narrow: allow what the job needs, require approval for changes and block the rest.
Blocked tools are removed from the tool list an app sees, so it won't try them. Because rules apply per app, the same Apify connection can be broad in one app and read-only in another, and the credential stays in Toolstile instead of each app's config file.
How it works with Toolstile
- Connect once. Add Apify to a workspace (browser sign-in). Toolstile keeps the credential, so no agent config holds it.
- Choose access per app. Give Claude Code every Apify tool, give Cursor only the read tools, or keep Apify away from an app entirely.
- Share approved accounts. Teammates use the connection without copying tokens, and you can remove access in one place.
- Review activity. See which app called which tool and when, so you can tighten access with evidence.
Add the Apify MCP server to an AI app
Through Toolstile, every AI app uses one gateway entry, whichever servers you connect. In Claude Code:
claude mcp add --transport http toolstile 'https://toolstile.com/mcp'Then connect Apify in your workspace and choose which of its tools that app may use. Client setup covers Codex, Cursor and Claude Desktop.
To connect directly instead, add the Apify endpoint to each app separately. In Claude Code:
claude mcp add --transport http apify 'https://mcp.apify.com'In Cursor's mcp.json:
{
"mcpServers": {
"apify": {
"url": "https://mcp.apify.com"
}
}
}Some servers accept only clients they have approved, or need a token header. Check the Apify MCP documentation for what your client needs.
Before you connect
An Apify account. Running Actors consumes your Apify usage.
Server details
| Detail | Value |
|---|---|
| Publisher | Apify |
| Endpoint | https://mcp.apify.com |
| Authentication | Browser sign-in |
| Categories | Marketing & research, Data & infrastructure |
| Tool list | 27 tools, observed 29 October 2026 (docs) |