Officially maintained by Apify, this MCP server exposes thousands of Apify Store Actors as callable AI-agent tools, supporting both a hosted streamable-http endpoint (OAuth or Bearer token) and a local stdio mode. It covers Actor discovery, execution, run management, and storage access, but requires an Apify account/token, incurs run costs, and collects telemetry by default.
Strongest · Documentation 17/20 Weakest · Security and permissions 8/20
Static review · not runListed 2026-08-06
Read the FMRS scoring method →Runtime：Hosted (no local runtime) · Node.js 22+
APIFY_TOKEN
Apify platform API token used to authenticate against the hosted server or local stdio run; available in your Apify account settings.
TELEMETRY_ENABLED
Set to false to disable telemetry and Sentry error tracking when running the local stdio server.
UI_MODE
Set to true to enable MCP Apps widget rendering in tool responses (also available via CLI flag).
APIFY_META_ORIGIN
Environment variable used when running the server locally for development (e.g., STANDBY), together with apify run.
Hosted (recommended): connect an OAuth-capable client (e.g. Claude.ai, VS Code) directly to the URL https://mcp.apify.com, or include an Authorization: Bearer <APIFY_TOKEN> header in requests; note the legacy /sse endpoint has been removed, so drop the /sse suffix and use the streamable-http URL. Local (stdio): set the MCP client's server command to npx @apify/actors-mcp-server and set the APIFY_TOKEN environment variable to your Apify API token; run npx @apify/actors-mcp-server --help for more options. A one-click .mcpb bundle install file is also available from the latest GitHub release.
{"mcpServers":{"apify":{"url":"https://mcp.apify.com","headers":{"Authorization":"Bearer <APIFY_TOKEN>"}}}}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"apify": {
"url": "https://mcp.apify.com",
"headers": {
"Authorization": "Bearer <APIFY_TOKEN>"
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add --transport http apify https://mcp.apify.com --header 'Authorization: Bearer <APIFY_TOKEN>'
Run it in a terminal; replace any <…> placeholders with your own values first.
After connecting to https://mcp.apify.com, tools like search-actors, fetch-actor-details, call-actor, and apify--rag-web-browser should appear in the client's tool list; calling search-actors for any Actor proves the connection works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
The Apify MCP Server (mcp.apify.com) lets AI agents extract data from social media, search engines, maps, e-commerce sites, and any other website using thousands of ready-made scrapers, crawlers, and automation tools from Apify Store. It supports OAuth login and Bearer-token authentication (Authorization: Bearer <APIFY_TOKEN>), so clients like Claude.ai or VS Code can connect using just the hosted URL, or it can be run locally over stdio via npx @apify/actors-mcp-server.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision 17e1e61cc336 Data synced 2026-11-04 Read the FMRS scoring method