Apify MCP Server
Official Apify MCP server: the agent runs ready-made Apify Store scrapers for social media, maps, search and shops
- 13,702 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs paid Actors on the user's account
- Sends queries and data to an external platform
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/apify-mcp-serverDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs paid Actors on the user's account
- Sends queries and data to an external platform
This is third-party code. Review the repository files before installing.
What it does
The server turns Apify Actors, ready-made scrapers and automations, into MCP tools. The agent searches the store for a fitting Actor, reads its input schema and runs it with the right parameters. By default it includes RAG Web Browser for search with page fetching and Web Fetch for getting a URL as Markdown. Any Actor can be added, for example for Instagram, Google Maps or Google results.
Who it is for. For marketers, analysts and developers who need an agent to collect web data with ready-made tools.
Good fit when
- You need posts or profiles from social networks
- You need contacts or places from Google Maps
- You need web search with page contents
Not a fit when
- You have no Apify account and do not want to pay for runs
- You need data from sites that no Actor covers
Example request
Find coffee shops in central Lisbon on Google Maps and put their phones and websites in a tableMCP
- Transport
- stdio, http
- Authentication
- OAuth
Environment variables
APIFY_TOKENrequired, secret- Apify API token for local runs
Limitations
Needs an APIFY_TOKEN or OAuth login, and Actor runs are billed at Apify rates. Some newer features, like output schema inference, exist only on the hosted server. Access to Apify from Russia without VPN is unverified. Respecting site terms when scraping is the user's responsibility.
How to disable. Remove the apify server from your MCP config or disconnect it in the client.
FAQ
Why prefer the hosted server?
It supports OAuth and newer features missing in stdio mode.
Can I pay without an account?
The README describes agentic payments via AGI, x402 and Skyfire, but they need a crypto wallet or a separate account.
Discussion
No questions or reviews yet.
Related
MCP serversOfficial Oxylabs MCP server: page scraping with JS rendering, Google and Amazon results, an AI crawler
Official Firecrawl MCP server: web search, page scraping to Markdown, site crawling and in-page actions
Hyperbrowser MCP
Hyperbrowser MCP Server
The official MCP server for Hyperbrowser cloud browsers: page scraping and crawling, structured data, Bing search and three browser agents
Official AgentQL MCP server: extracts structured data from a web page based on a field description
MCP servers for marketplace search via Apify
Marketplaces MCP Servers
Three MCP servers that search products on Wildberries, Ozon and Yandex Market through Apify actors, with caching and compact output for agent context
Official Tavily MCP server: real-time web search, page content extraction, site mapping and crawling
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Apify MCP Server (this entry) | yes | OAuth | 13,702 | |
| Awesome Apify Skills | no | 283 | a community collection of Apify skills | |
| ScrapeAtlas CLI | yes | official ScrapeAtlas terminal client |
README in short
The README offers two ways to connect: a hosted endpoint with OAuth or token and local launch via npx. It lists tested clients, an MCPB file for one-click install, tools for finding and running Actors, resources and prompts. A separate section covers agentic payments. MIT licensed.