Apify MCP

What it does

Runs Apify actors on demand and hands their output back as context: scrapers, crawlers, search, and document extractors behind one interface. The hosted endpoint handles OAuth; the local package keeps the process on your machine and takes a token explicitly. Worth it if your scraping already lives in Apify, less so if it does not.

Install

npx @apify/actors-mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com"
    }
  }
}

When to use it

Reach for this when the task needs scraping inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

• Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
• Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
• Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude