Actors

The Apify MCP Server lets your AI assistant call any Apify Actor as a tool for web scraping, data extraction, and automation in real time. It connects applications to thousands of ready-built actors, enabling powerful, context-aware actions through a simple MCP interface.

How to use

Connect your MCP client to the hosted server at https://mcp.apify.com to access a broad set of Apify Actors. You can authorize with OAuth or provide an API token via the Authorization: Bearer <APIFY_TOKEN> header. This setup allows your AI assistant to discover actors dynamically, pick the right tool for a task, and pass inputs automatically.

How to install

Prerequisites: Node.js (v18 or higher) and an Apify API token.

Choose one of the two connection methods below. Use the hosted MCP server for the easiest setup, or run a local stdio server for development and testing.

Hosted MCP server (recommended for most use cases) simply connects your MCP client to the remote endpoint at https://mcp.apify.com.

Local stdio MCP server (for developers and testers) use this command to start the server and connect your client.

Local stdio startup involves running the MCP server via npx @apify/actors-mcp-server with your token set in the environment.

Additional sections

Tools, resources, and prompts describe how you can leverage the full MCP toolset to discover and manage Apify Actors, fetch documentation, access datasets, and more. You can enable advanced tool categories like docs, runs, storage, and preview as needed.

Troubleshooting common issues (local MCP server): ensure Node.js is installed, set APIFY_TOKEN correctly, and keep the MCP server up to date with the latest package.

Development notes cover prerequisites, building the server package, and starting HTTP streamable or stdio MCP servers for testing and canary releases.

Tools, resources, and prompts

The MCP server exposes a collection of actor-driven tools. You can discover new actors on the fly, run actor tasks, and retrieve logs and results.

Contributing

Contributions are welcome. Share issues, submit improvements, and provide new examples to help others use Apify MCP effectively.

Learn more

Explore topics about Model Context Protocol, AI agents, and how to build and use MCP-powered workflows with Apify Actors.

Available tools

get-actor-details

Retrieve detailed information about a specific Actor.

search-actors

Search for Actors in the Apify Store.

add-actor

Add an Actor as a new tool for the user to call.

apify-slash-rag-web-browser

An Actor tool to browse the web.

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.

call-actor

Call an Actor and get its run results.

get-actor-run

Get detailed information about a specific Actor run.

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-items

Retrieve items from a dataset with support for filtering and pagination.

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-key-value-store-record

Get the value associated with a specific key in a 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.