Apify MCP Server

apify/apify-mcp-serverOfficial

The Apify MCP Server enables AI agents to extract data from websites by integrating with thousands of ready-made scrapers, crawlers, and automation tools from the Apify Store, covering social media, search engines, maps, e-commerce sites, and other web sources. It provides tools to run these Actors directly through the Model Context Protocol, with support for OAuth authentication and agentic payments via x402 and Skyfire protocols. The server solves the problem of enabling AI assistants to autonomously gather structured web data without requiring users to build custom scrapers or manage direct API authentication.

GitHub stars: 16K
tools: 8
auth: Secret needed
transport: HTTP
last updated: Nov 12, 2026

View on GitHub

Tools

8 tools

Public tool metadata for what this MCP can expose to an agent.

search-actorsSearch the Apify Store to FIND and DISCOVER what scraping tools/Actors exist for specific platforms or use cases. This tool provides INFORMATION about available Actors - it does NOT retrieve actual data or run any scraping tasks. Do NOT use this tool for helper name resolution...3 params

Search the Apify Store to FIND and DISCOVER what scraping tools/Actors exist for specific platforms or use cases. This tool provides INFORMATION about available Actors - it does NOT retrieve actual data or run any scraping tasks. Do NOT use this tool for helper name resolution...

Parameters* required

keywordsstring

Space-separated keywords used to search pre-built solutions (Actors) in the Apify Store. The search engine searches across Actor's name, description, username, and readme content. Follow these rul...default:

limitinteger

The maximum number of Actors to return (default = 5)default: 5

offsetinteger

The number of elements to skip from the start (default = 0)default: 0

fetch-actor-detailsGet detailed information about an Actor by its ID or full name (format: "username/name", e.g., "apify/rag-web-browser"). Use 'output' parameter with boolean flags to control returned information: - Default: All fields true except mcpTools - Selective: Set desired fields to tru...2 params

Get detailed information about an Actor by its ID or full name (format: "username/name", e.g., "apify/rag-web-browser"). Use 'output' parameter with boolean flags to control returned information: - Default: All fields true except mcpTools - Selective: Set desired fields to tru...

Parameters* required

actorstring

Actor ID or full name in the format "username/name", e.g., "apify/rag-web-browser".

outputobject

Specify which information to include in the response to save tokens.

call-actorCall any Actor from the Apify Store. WORKFLOW: 1. Use fetch-actor-details to get the Actor's input schema 2. Call this tool with the actor name and proper input based on the schema If the actor name is not in "username/name" format, use search-actors to resolve the correct Act...5 params

Call any Actor from the Apify Store. WORKFLOW: 1. Use fetch-actor-details to get the Actor's input schema 2. Call this tool with the actor name and proper input based on the schema If the actor name is not in "username/name" format, use search-actors to resolve the correct Act...

Parameters* required

actorstring

The name of the Actor to call. Format: "username/name" (e.g., "apify/rag-web-browser"). For MCP server Actors, use format "actorName:toolName" to call a specific tool (e.g., "apify/actors-mcp-serv...

asyncboolean

When true, starts the run and returns immediately with runId. When false or omitted, behavior depends on the active server mode/tool variant. IMPORTANT: use async=true only when the user explicitly...

callOptionsobject

Optional call options for the Actor run configuration.

inputobject

The input JSON to pass to the Actor. Required.

previewOutputboolean

When true (default): includes preview items. When false: metadata only (reduces context). Use when fetching fields via get-actor-output.

get-actor-runGet detailed information about a specific Actor run by runId. The results will include run metadata (status, timestamps), performance stats, and resource IDs (datasetId, keyValueStoreId, requestQueueId). CRITICAL WARNING: NEVER call this tool immediately after call-actor in UI...1 params

Get detailed information about a specific Actor run by runId. The results will include run metadata (status, timestamps), performance stats, and resource IDs (datasetId, keyValueStoreId, requestQueueId). CRITICAL WARNING: NEVER call this tool immediately after call-actor in UI...

Parameters* required

runIdstring

The ID of the Actor run.

get-actor-outputRetrieve the output dataset items of a specific Actor run using its datasetId. You can select specific fields to return (supports dot notation like "crawl.statusCode") and paginate results with offset and limit. This tool is a simplified version of the get-dataset-items tool,...4 params

Retrieve the output dataset items of a specific Actor run using its datasetId. You can select specific fields to return (supports dot notation like "crawl.statusCode") and paginate results with offset and limit. This tool is a simplified version of the get-dataset-items tool,...

Parameters* required

datasetIdstring

Actor output dataset ID to retrieve from.

fieldsstring

Comma-separated list of fields to include (supports dot notation like "crawl.statusCode"). For example: "crawl.statusCode,text,metadata"

limitnumber

Maximum number of items to return (default: 100).default: 100

offsetnumber

Number of items to skip (default: 0).default: 0

search-apify-docsSearch Apify and Crawlee documentation using full-text search. You must explicitly select which documentation source to search using the docSource parameter: • docSource="apify" - Apify: Apify Platform documentation including: Platform features, SDKs (JS, Python), CLI, REST AP...4 params

Search Apify and Crawlee documentation using full-text search. You must explicitly select which documentation source to search using the docSource parameter: • docSource="apify" - Apify: Apify Platform documentation including: Platform features, SDKs (JS, Python), CLI, REST AP...

Parameters* required

docSourcestring

Documentation source to search. Defaults to "apify". • "apify" - Apify • "crawlee-js" - Crawlee (JavaScript) • "crawlee-py" - Crawlee (Python)one of apify · crawlee-js · crawlee-pydefault: apify

limitnumber

Maximum number of search results to return. Defaults to 5. Maximum is 20. You can increase this limit if you need more results, but keep in mind that the search results are limited to the most rele...default: 5

offsetnumber

Offset for the search results. Defaults to 0. Use this to paginate through the search results. For example, if you want to get the next 5 results, set the offset to 5 and limit to 5.default: 0

querystring

Algolia full-text search query to find relevant documentation pages. Use only keywords, do not use full sentences or questions. For example, "standby actor" will return documentation pages that con...

fetch-apify-docsFetch the full content of an Apify or Crawlee documentation page by its URL. Use this after finding a relevant page with the search-apify-docs tool. USAGE: - Use when you need the complete content of a specific docs page for detailed answers. USAGE EXAMPLES: - user_input: Fetc...1 params

Fetch the full content of an Apify or Crawlee documentation page by its URL. Use this after finding a relevant page with the search-apify-docs tool. USAGE: - Use when you need the complete content of a specific docs page for detailed answers. USAGE EXAMPLES: - user_input: Fetc...

Parameters* required

urlstring

URL of the Apify documentation page to fetch. This should be the full URL, including the protocol (e.g., https://docs.apify.com/).

apify-slash-rag-web-browserThis tool calls the Actor "apify/rag-web-browser" and retrieves its output results. Use this tool instead of the "call-actor" if user requests this specific Actor. Actor description: Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in Ch...3 params

This tool calls the Actor "apify/rag-web-browser" and retrieves its output results. Use this tool instead of the "call-actor" if user requests this specific Actor. Actor description: Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in Ch...

Parameters* required

maxResultsinteger

The maximum number of top organic Google Search results whose web pages will be extracted. If `query` is a URL, then this field is ignored and the Actor only fetches the specific web page. Example...default: 3

outputFormatsarray

Select one or more formats to which the target web pages will be extracted and saved in the resulting dataset. Example values: ["markdown"]

querystring

**REQUIRED** Enter Google Search keywords or a URL of a specific web page. The keywords might include the [advanced search operators](https://blog.apify.com/how-to-scrape-google-like-a-pro/). Examp...

Readme

Apify MCP server

View the full README on GitHub

Details

Repository: github.com/apify/apify-mcp-server
Website: mcp.apify.com
Categories: Search & Web Crawling, Data & Analytics
Transport: HTTP
Auth: Required
Registry: MCP registry, active

Related Search & Web Crawling MCP servers

View all

Obscurah4ckf0r0day/obscuraThe headless browser for AI agents and web scraping. Rust, anti-detection, CDP-compatible, with a built-in MCP server.15.7Kstars

Search Google Flightspunitarani/fliSearch for Flights on Google Flights. You can search for the cheapest days to fly and also the specific flight information.3Kstars

Hyperbrowserhyperbrowserai/mcpProvides data scraping, structured data extraction, and web crawling through MCP clients with browser-use agents.761stars

OpenBrandethanjyx/openbrandExtract brand assets (logos, colors, backdrop images, brand name) from any website URL751stars

XActionsnirholas/xactionsX/Twitter automation MCP: scrape, post, schedule, analyze, engage. No API key required.644stars