{"type":"mcp_server","name":"actors-mcp-server","description":"This repository implements an MCP server for Apify Actors, enabling AI assistants to use them as tools for tasks like data extraction and web scraping via HTTP or standard input/output.","category":"AI","language":"TypeScript","stars":1475,"forks":8,"owner":"apify","github_url":"https://github.com/apify/actors-mcp-server","homepage":"https://apify.com/apify/actors-mcp-server","setup":"## Setup\n\n**MCP Server Actor (via Apify platform):**\n\n1.  Start server with default Actors by sending an HTTP GET request with your Apify API token to `https://actors-mcp-server.apify.actor?token=<APIFY_TOKEN>`. \n2.  Alternatively, create a task with a specific list of Actors and run it in Standby mode using a URL like `https://USERNAME--actors-mcp-server-task.apify.actor?token=<APIFY_TOKEN>`. \n3.  Interact with the server over SSE using the Tester MCP Client or `curl` commands.\n4.  For SSE interaction, initiate SSE with `curl https://actors-mcp-server.apify.actor/sse?token=<APIFY_TOKEN>` and send messages with `curl -X POST \"https://actors-mcp-server.apify.actor/message?token=<APIFY_TOKEN>&session_id=a1b\" -H \"Content-Type: application/json\" -d '{...}'`.\n\n**MCP Server at a local host:**\n\n1.  Prerequisites: MacOS or Windows, Claude Desktop (or another MCP client), Node.js (v18+), Apify API Token (`APIFY_TOKEN`).\n2.  Configure Claude Desktop: Enable Developer Mode, edit the configuration file (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS or `%APPDATA%/Claude/claude_desktop_config.json` on Windows), and add the `mcpServers` configuration.\n3.  Example `mcpServers` configuration:\n\n    ```json\n    {\n     \"mcpServers\": {\n       \"actors-mcp-server\": {\n         \"command\": \"npx\",\n         \"args\": [\"-y\", \"@apify/actors-mcp-server\"],\n         \"env\": {\n            \"APIFY_TOKEN\": \"your-apify-token\"\n         }\n       }\n     }\n    }\n    ```\n4.  Restart Claude Desktop and verify the connection with the 🔌 icon.\n5.  Alternatively, install via Smithery: `npx -y @smithery/cli install @apify/actors-mcp-server --client claude`.\n6.  For Stdio clients, create a `.env` file with `APIFY_TOKEN` and optionally `ANTHROPIC_API_KEY`.\n7.  Run `clientStdio.ts` or `clientStdioChat.ts` from the `examples` directory using `node dist/examples/clientStdio.js` or `node dist/examples/clientStdioChat.js`.\n8.  Debugging: Use the MCP Inspector with `export APIFY_TOKEN=your-apify-token` and `npx @modelcontextprotocol/inspector node ./dist/index.js`.\n","tools":"## Available Tools\n\n1.  **Apify Actors** (Any Apify Actor can be used as a tool, pre-configured with `apify/instagram-scraper`, `apify/rag-web-browser`, and `lukaskrivka/google-maps-with-contact-details` by default).\n2.  **`get-actor-details`** (Retrieves documentation, input schema, and details about a specific Actor).\n3.  **`discover-actors`** (Searches for relevant Actors using keywords and returns their details).\n4.  **`add-actor-as-tool`** (Adds an Actor by name to the available tools list without executing it).\n5.  **`remove-actor-from-tool`** (Removes an Actor by name from the available tools list when it's no longer needed).\n","faq":null,"created_at":"2025-01-02T15:43:09+00:00","updated_at":"2025-03-28T23:45:16+00:00","source_url":"https://model-context-protocol.com/servers/apify-actors-model-context-protocol-server","related_articles":[]}