X's own hosted MCP server: full-archive post search, user and timeline lookup, trends, bookmarks and article drafting, under your account's permissions.
Apify ActorsMCP Server
Summary
Apify's official MCP server — turn thousands of ready-made scrapers into tools your assistant can call.
Features
- Call thousands of maintained scrapers as tools
- Search the Actor store and add tools dynamically
- Structured results from sites with no public API
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
Apify's official MCP server exposes its Actor marketplace to an AI assistant, which is an efficient way to give an agent web-data capabilities without building any scrapers.
What it unlocks
Thousands of maintained Actors covering search engines, social platforms, marketplaces, maps, job boards, review sites, and general-purpose crawling. Each one has a documented input schema, so the assistant knows what parameters to supply, and returns structured data rather than HTML.
How it works
- Dynamic tool discovery. The assistant can search the Actor store and add relevant Actors as tools mid-conversation, rather than being limited to a preconfigured list.
- Direct execution of any Actor with parameters, returning the dataset it produces.
- Dataset access for retrieving results from past runs.
Why it beats writing a scraper
Actors are maintained by their authors. When a target site changes its markup, someone else fixes it. For an agent that needs data from a dozen different sites, that maintenance difference is the whole argument.
Requires an Apify account and token; runs with npx -y @apify/actors-mcp-server. Free monthly credits cover light use.
Related MCP Servers
Official MCP server for Meilisearch — create and configure indexes, add documents, run hybrid and semantic searches, and manage API keys and tasks through conversation.
Browserbase's official MCP server — cloud browser automation with Stagehand's natural-language actions.
Private, self-hosted web search for AI assistants via SearXNG, with pagination, filters, and URL-to-markdown reading.