Actors MCP Server
Pricing
Pay per usage
Actors MCP Server
Connect Apify Actors to AI applications (AI Agents) using Anthropic's Model Context Protocol (MCP). This MCP server provides integration of any Apify Actor through the MCP framework.
4.6 (6)
Pricing
Pay per usage
47
Total users
1.1k
Monthly users
565
Runs succeeded
89%
Issue response
3 days
Last modified
7 days ago
You can access the Actors MCP Server programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youโll need an Apify account and your API token, found in Integrations settings in Apify Console.
$# Start Server-Sent Events (SSE) session and keep it running<curl "https://actors-mcp-server.apify.actor/sse?token=<YOUR_API_TOKEN>&actors=apify/actors-mcp-server"
# Session id example output:# event: endpoint# data: /message?sessionId=9d820491-38d4-4c7d-bb6a-3b7dc542f1faUsing Actors MCP Server via Model Context Protocol (MCP) server
MCP server lets you use Actors MCP Server within your AI workflows. Send API requests to trigger actions and receive real-time results. Take the received sessionId and use it to communicate with the MCP server. The message starts the Actors MCP Server Actor with the provided input.
$curl -X POST "https://actors-mcp-server.apify.actor/message?token=<YOUR_API_TOKEN>&session_id=<SESSION_ID>" -H "Content-Type: application/json" -d '{$ "jsonrpc": "2.0",$ "id": 1,$ "method": "tools/call",$ "params": {$ "arguments": {$ "actors": [$ "apify/instagram-scraper",$ "apify/rag-web-browser",$ "lukaskrivka/google-maps-with-contact-details"$ ],$ "maxActorMemoryBytes": 4096,$ "debugActor": "apify/rag-web-browser",$ "debugActorInput": {$ "query": "hello world"$ }$},$ "name": "apify/actors-mcp-server"$ }$}'The response should be: Accepted. You should received response via SSE (JSON) as:
$event: message$data: {$ "result": {$ "content": [$ {$ "type": "text",$ "text": "ACTOR_RESPONSE"$ }$ ]$ }$}Configure local MCP Server via standard input/output for Actors MCP Server
You can connect to the MCP Server using clients like ClaudeDesktop and LibreChat or build your own. The server can run both locally and remotely, giving you full flexibility. Set up the server in the client configuration as follows:
{ "mcpServers": { "actors-mcp-server": { "command": "npx", "args": [ "-y", "@apify/actors-mcp-server", "--actors", "apify/actors-mcp-server" ], "env": { "APIFY_TOKEN": "<YOUR_API_TOKEN>" } } }}You can further access the MCP client through the Tester MCP Client, a chat user interface to interact with the server.
To get started, check out the documentation and example clients. If you are interested in learning more about our MCP server, check out our blog post.
