Apify Actors MCP Server
by apify
Expose Apify Actors as individual MCP tools for your AI agent
data Node.js Intermediate Self-hostable No API key
β 798 stars π
Updated: yesterday
Description
Apify Actors MCP Server is the companion project to the main Apify MCP Server, but with a different approach. Instead of giving your agent a generic interface to browse and run any Actor, this server lets you select specific Actors and expose each one as a dedicated MCP tool. The result is a more focused, discoverable interface β your agent sees named tools like "scrape_google_maps" or "extract_linkedin_profiles" rather than a generic "run_actor" command.
This design choice matters for agent usability. When an MCP client shows your agent a list of available tools, having purpose-specific names and descriptions helps the agent pick the right tool for the task. It is the difference between a toolbox with labeled drawers and one where everything is in a single bin. You configure which Actors to expose, and the server generates properly typed MCP tools for each.
The project shares the same codebase and maintenance team as the main Apify MCP server (same repo, 798 stars). It is particularly useful when you have a curated set of Actors your team uses regularly and want your agent to access them by name without browsing the full marketplace each time.
β Best for
Teams with a fixed set of Apify Actors they use regularly and want clean MCP tool integration
βοΈ Skip if
You want to explore Apify's full Actor catalogue dynamically β use the main Apify MCP server instead
π‘ Use cases
- Create a curated set of scraping tools for your agent from specific Apify Actors
- Give your agent named, purpose-specific tools instead of a generic Actor runner
- Build domain-specific AI workflows where each step uses a different pre-configured Actor
π Pros
- β Each Actor becomes a named, discoverable MCP tool with proper descriptions
- β Better agent UX β purpose-specific tools are easier for AI models to select correctly
- β Same reliability and maintenance as the main Apify MCP server
π Cons
- β Requires manual configuration to select which Actors to expose as tools
- β Less flexible than the main server β you cannot browse or discover new Actors on the fly
- β Still depends on Apify's paid platform for actual Actor execution
π‘ Tips & tricks
Start by identifying the 3-5 Actors your team uses most frequently and expose only those.
A focused toolset helps your agent make better decisions than exposing dozens of tools.
Use descriptive names in the configuration β "extract_product_prices" is better than
"actor_abc123" for agent discoverability.
Quick info
- Author
- apify
- License
- MIT
- Runtime
- Node.js
- Transport
- stdio
- Category
- data
- Difficulty
- Intermediate
- Self-hostable
- β
- API key
- No API key needed
- Docker
- β
- Version
- 0.0.0
- Updated
- Feb 21, 2026
Client compatibility
- β Claude Code
- β Cursor
- β VS Code Copilot
- β Gemini CLI
- β Windsurf
- β Cline
- β JetBrains AI
- β Warp
Platforms
π macOS π§ Linux πͺ Windows