Connect AI agents to thousands of tools via a protocol server
Top 93.9% on sourcepulse
This repository provides the Apify Model Context Protocol (MCP) Server, enabling AI assistants to leverage thousands of pre-built web scraping and automation tools (Apify Actors). It targets AI developers and researchers looking to integrate real-world data extraction and task execution into their AI agents, offering a seamless way to connect LLMs to practical automation capabilities.
How It Works
The MCP Server acts as a bridge between AI agents and the Apify platform. It dynamically discovers Apify Actors, translates their input schemas into MCP-compatible tools, and facilitates real-time execution. This approach allows AI agents to interact with complex automation tasks without needing explicit integration code for each Actor, leveraging the LLM's understanding of natural language to select and configure the appropriate tool.
Quick Start & Requirements
https://mcp.apify.com
(supports OAuth, recommended).npx @apify/actors-mcp-server
. Requires APIFY_TOKEN
environment variable.Highlighted Details
apify/rag-web-browser
and other utility tools.Maintenance & Community
The project is actively maintained by Apify. Contributions are welcomed via issues and pull requests. Further resources and community links are available on the project's documentation pages.
Licensing & Compatibility
The repository does not explicitly state a license in the provided README. Compatibility for commercial use or closed-source linking would require clarification on the licensing terms.
Limitations & Caveats
Actor input schemas are modified for client compatibility, including description truncation and enum length limits. Rental Actors are only accessible via the hosted endpoint; local stdio usage is limited to locally configured Actors. Some helper tools require explicit enabling.
2 days ago
Inactive