Skip to content

MCP server

Apify MCP server

Apify's official MCP server lets AI find and run ready-made scrapers and automation tools, called Actors, and read their results.

At a glance

Maintained by
Apify
Tools exposed
9 listed below
Reviewed
September 24, 2026

Why it matters

What it does and why it matters

Apify runs a large store of ready-made scrapers and automation tools, called Actors, for sites such as maps, marketplaces and social networks. Its official MCP server lets an assistant search that store, read an Actor's details, run it, check the run and read the results.

That means an assistant can collect structured data from many sources without anyone writing a scraper. Ask for local businesses in a city or reviews of a product, and it can find a suitable Actor and run it.

Running Actors uses paid Apify credits, so an agent with this server can spend money. We set a budget in the Apify account, limit which Actors may be called and require approval before large runs. The older SSE endpoint was removed, so use the current hosted address.

Check each source site's terms before collecting data, and handle any personal data in results according to privacy rules.

Use cases

Best business use cases

Local lead lists

Collect public business listings for a region. See AI sales research.

Review collection

Gather public reviews for analysis. See feedback analysis.

Marketplace prices

Track public marketplace prices. See price monitoring.

Content monitoring

Collect public posts or news on a topic.

Apify docs

Search Apify documentation while building.

Tools

Available tools

Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.

Read and write: Read and write: searches and reads data, and can start or abort paid scraper runs; optional tools create tasks and schedules.

  • search-actors

    Search for Actors in Apify Store.

  • fetch-actor-details

    Get an Actor's input schema, README, pricing and output schema.

  • call-actor

    Run an Actor and get its results.

  • get-actor-run

    Get details about a specific Actor run.

  • get-dataset-items

    Read items from a dataset with filtering and pagination.

  • get-key-value-store-record

    Get a value by key from a key-value store.

  • abort-actor-run

    Stop a running Actor run.

  • search-apify-docs

    Search the Apify documentation.

  • fetch-apify-docs

    Fetch the full text of an Apify docs page.

Workflows

Example workflows

Build a local prospect list

  1. 1

    Ask for businesses of a type in a city.

  2. 2

    The assistant searches for a suitable Actor.

  3. 3

    It shows the Actor details and expected cost.

  4. 4

    You approve the run.

  5. 5

    It reads the dataset and returns a clean list.

Monthly review snapshot

  1. 1

    Choose products to track.

  2. 2

    The assistant runs the review Actor with limits.

  3. 3

    It reads the results.

  4. 4

    It groups reviews by theme.

  5. 5

    It sends a short summary.

Prompts

Example prompts

  • “Find an Actor that collects public business listings and show me its cost before running it.”

  • “Run it for dental clinics in Austin and return name, address and website.”

  • “Summarize the latest 200 reviews collected for our product.”

Setup

Installation and configuration

Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.

Claude Desktop: claude_desktop_config.json

{
    "mcpServers": {
        "actors-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "@apify/actors-mcp-server"
            ],
            "env": {
                "APIFY_TOKEN": "YOUR_APIFY_TOKEN"
            }
        }
    }
}

Claude Code: terminal

claude mcp add --transport http apify https://mcp.apify.com
  • Hosted server: streamable-http; https://mcp.apify.com; OAuth, or header Authorization: Bearer <APIFY_TOKEN>.
  • Local server: stdio; @apify/actors-mcp-server.
  • Needs: APIFY_TOKEN (local, or bearer header on remote; OAuth also supported on remote).

Security

Security considerations

  • Spending

    Runs use paid credits. Set account limits and approve large runs.

  • Allowed Actors

    Limit which Actors the assistant may call.

  • Site terms

    Respect source site terms and privacy rules.

  • Token safety

    Keep the Apify token out of shared files.

Related servers

Servers that pair well with it

Firecrawl

Firecrawl's official MCP server lets AI scrape, map, crawl and search the web and get clean, AI-ready content back.

Playwright

Microsoft's Playwright MCP server lets AI drive a real browser: open pages, read them, click, type, fill forms and take screenshots.

Browserbase

Browserbase's hosted MCP server gives AI a cloud browser that can browse, act on pages, observe elements and extract data.

Keep exploring

FAQ

Questions people ask us

Have a question that is not here? Ask us directly.

Start a project

Want this connected to your own systems? We build AI workflows with MCP.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.