← Back to directory
A

Apify MCP Server

Official
Turn thousands of Apify Actors into AI-agent tools for web scraping and data extraction.
GitHub source repository ↗
★ 2.6k Stars Category · Other Very popular
64FMRS · C
Reliability
10/20
Security and permissions
8/20
Maintenance
15/20
Documentation
17/20
Setup experience
14/20

Officially maintained by Apify, this MCP server exposes thousands of Apify Store Actors as callable AI-agent tools, supporting both a hosted streamable-http endpoint (OAuth or Bearer token) and a local stdio mode. It covers Actor discovery, execution, run management, and storage access, but requires an Apify account/token, incurs run costs, and collects telemetry by default.

Read the FMRS scoring method →

The Apify MCP Server (mcp.apify.com) lets AI agents extract data from social media, search engines, maps, e-commerce sites, and any other website using thousands of ready-made scrapers, crawlers, and automation tools from Apify Store. It supports OAuth login and Bearer-token authentication (Authorization: Bearer <APIFY_TOKEN>), so clients like Claude.ai or VS Code can connect using just the hosted URL, or it can be run locally over stdio via npx @apify/actors-mcp-server.

Tools

search-actors
Search for Actors in Apify Store.
fetch-actor-details
Retrieve detailed information about a specific Actor, including its input schema, README (summary when available, full otherwise), pricing, and output schema.
call-actor
Call an Actor and get its run results. Use fetch-actor-details first to get the Actor's input schema.
get-actor-run
Get detailed information about a specific Actor run.
get-dataset-items
Retrieve items from a dataset with support for filtering and pagination.
get-key-value-store-record
Get the value associated with a specific key in a key-value store.
abort-actor-run
Abort a running Actor run, optionally gracefully.
search-apify-docs
Search the Apify documentation for relevant pages.
fetch-apify-docs
Fetch the full content of an Apify documentation page by its URL.
apify--rag-web-browser
A pre-configured Actor tool used to browse the web, search, and return top-result content.
report-problem
Report a problem with an Apify tool or Actor to the Apify team.
get-actor-run-list
Get a list of an Actor's runs, filterable by status.
get-actor-log
Retrieve the logs for a specific Actor run.
get-dataset
Get metadata about a specific dataset.
get-dataset-schema
Generate a JSON schema from dataset items.
get-key-value-store
Get metadata about a specific key-value store.
get-key-value-store-keys
List the keys within a specific key-value store.
get-dataset-list
List all available datasets for the user.
get-key-value-store-list
List all available key-value stores for the user.

Setup

Hosted (recommended): connect an OAuth-capable client (e.g. Claude.ai, VS Code) directly to the URL https://mcp.apify.com, or include an Authorization: Bearer <APIFY_TOKEN> header in requests; note the legacy /sse endpoint has been removed, so drop the /sse suffix and use the streamable-http URL. Local (stdio): set the MCP client's server command to npx @apify/actors-mcp-server and set the APIFY_TOKEN environment variable to your Apify API token; run npx @apify/actors-mcp-server --help for more options. A one-click .mcpb bundle install file is also available from the latest GitHub release.

claude_desktop_config.json
{"mcpServers":{"apify":{"url":"https://mcp.apify.com","headers":{"Authorization":"Bearer <APIFY_TOKEN>"}}}}

Fit and risk

Best for

  • Developers adding web scraping/data extraction capabilities to AI agents without building their own crawlers
  • Users of Claude, Cursor, VS Code, or ChatGPT who want dynamic discovery and use of Apify Store scraping tools
  • Autonomous agents that need to pay per Actor run via prepaid tokens (AGI, x402, or Skyfire)

Not for

  • Tasks that don't need internet scraping, such as pure local filesystem or database work
  • Users without an Apify account who are unwilling to authenticate via OAuth or API token
  • Fully offline setups that must avoid sending any data to the Apify platform

Required permissions

  • Requires an Apify API token (Bearer) or OAuth login to an Apify account
  • Runs Actors and reads run status, dataset, and key-value store data on behalf of the user's account
  • Needs outbound network access to reach the Apify API and the external websites Actors scrape

Risks and side effects

  • Running Actors incurs cost, paid via prepaid balance, AGI, direct x402, or Skyfire
  • Telemetry (tool-call usage data) is collected by default, and stdio mode also enables Sentry error tracking by default unless opted out
  • Dynamic tool discovery lets the agent invoke arbitrary third-party Actors from Apify Store, whose behavior and data handling are outside this server's control
  • Scraped website data passes through the Apify API; users are responsible for ensuring scraping complies with target sites' terms of service

Troubleshooting

  1. Confirm APIFY_TOKEN is set correctly (local stdio) or OAuth authorization completed (hosted)
  2. Confirm you are not using the removed `/sse` endpoint — use `https://mcp.apify.com` instead
  3. For local development, confirm Node.js v22+ is installed and `pnpm run build` has been run
  4. Use MCP Inspector against `http://localhost:3001` (HTTP mode) or `./dist/stdio.js` (stdio mode) to debug
  5. Check the `tools` query parameter/CLI flag configuration, since default tool sets may change in future versions
  6. Disable telemetry/Sentry reporting with `--telemetry-enabled=false` or `TELEMETRY_ENABLED=false` if needed

Use cases

Scrape posts from Facebook pages/profiles
Extract contact details from Google Maps listings
Scrape Google Search Engine Results Pages (SERPs)
Scrape Instagram posts, profiles, places, photos, and comments
Search the web and retrieve top-result content with RAG Web Browser

Supported clients

Claude DesktopFull support
Claude.aiFull support
Claude CodeFull support
CursorFull support
VS CodeFull support
ChatGPTFull support
OpenCodePartial support
KiroPartial support
Apify Tester MCP ClientFull support