AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Browser Automation/
apify-mcp-server
apify-mcp-server logo

apify-mcp-server

Active·★ 12.6k·MIT·Updated 2026-10-22
★ Most Popular

The Apify MCP Server lets an AI assistant use any Apify Actor as a tool. An Actor is a ready-made cloud program on the Apify platform that performs a specific job, such as extracting data from social media, search engines, maps or e-commerce sites. Instead of one scraper, the server gives an agent a catalogue of thousands of them, plus documentation search and Apify's RAG web browser and web fetch tools.

It suits teams who want agents to collect data from many different kinds of sites without writing or maintaining scrapers. Apify recommends its hosted server at mcp.apify.com, which supports the latest features; the older SSE endpoint has been removed in favour of Streamable HTTP, so clients must use the main URL. You can limit which tools are exposed (for example only the Actors you need) to save context, and the server works with Claude Code, Claude.ai, Cursor, VS Code and other MCP clients. It also supports agentic payments, so an agent can pay to run Actors, and collects telemetry that can be disabled.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

Getting started: create an Apify account and API token, then connect your client to the hosted server, or run it locally with `npx @apify/actors-mcp-server` and set `APIFY_TOKEN`. Use the `--tools` option to expose only specific Actors, and `--telemetry-enabled=false` if you want to opt out of telemetry.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-17.

License
MIT
Latest release
v0.18.4 · 2026-10-16
Last commit
2026-10-16
Contributors
51
Forks
415
Open issues and PRs
201
First published
2025-01-02
npm package
@apify/actors-mcp-server 0.18.4 · 17,093 downloads last week

Source: GitHub, npm and PyPI public APIs.

#AI Agents#Data Extraction#Web Scraping#Automation#Model Context Protocol#Apify#OAuth
$ Install
$ npx @apify/actors-mcp-server
↗ Visit site★ GitHub
01

Features

01Integrate any Apify Actor as an AI agent tool.
02Support for OAuth and API token authentication.
03Enable agentic payments via Skyfire integration.
04Dynamic discovery of Apify Actors and helper tools.
05Offers both a hosted HTTPS endpoint and local standard I/O server options.
02

Why choose it

+Access to a very large catalogue of ready-made scrapers instead of a single tool.
+Hosted server means no local setup, and tools can be restricted to save context.
+Works with major MCP clients; MIT licensed.
+Supports agent payments for running paid Actors.
03

Trade-offs

!Running Actors uses the paid Apify platform; costs depend on the Actor and usage.
!Third-party Actors vary in quality and in what they collect; check an Actor's documentation and terms before pointing an agent at it.
!Telemetry is on by default and must be turned off explicitly if you do not want it, and the legacy SSE transport no longer works.
05

Maintenance check

ActiveChecked: 2026-10-22
Last commit
2026-10-21
Commits, last 90 days
100+
Releases, last 90 days
28
Latest release
v0.19.3 (2026-10-21)
Open issues
232
Recent issues with at least one comment
1/26
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 15, 14, 26, 13, 17, 17, 13, 20, 17, 37, 71, 25

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

04

Who it fits

Pick it if
  • You want AI agents to invoke thousands of battle-tested cloud scrapers from the Apify Store (social media, Google Maps, Amazon, real estate).
  • You want serverless data extraction with managed proxy pools and anti-bot bypass without maintaining local browser clusters.
Look elsewhere if
  • You are scraping simple static sites without anti-bot blocks where free local libraries (Scrapling, Crawl4AI) are more cost-effective.
  • Strict data compliance prevents sending scraping target URLs and credentials through external third-party cloud infrastructure.
06

How it differs

Scrapling logovs Scrapling★ 89.2k

apify-mcp-server relies on managed cloud scrapers and residential proxy pools; Scrapling is a free local Python library with undetectable fingerprinting.

Full comparison →
brightdata-mcp logovs brightdata-mcp★ 2.7k

Both are top-tier commercial data extraction providers: Apify shines with pre-built community Actors; Bright Data excels in global proxy networks and Web Unlocker.

Full comparison →
07

Compatibility

Claude.ai (web)
Client
Verified via docs
Claude Desktop
Client
Verified via docs
VS Code (Genie)
Client
Verified via docs
Cursor
Client
Verified via docs
Apify Tester MCP Client
Client
Verified via docs
OpenCode
Client
Verified via docs
08

Quick start

1
$ npx @apify/actors-mcp-server
09

Use cases

↳Extracting data from social media platforms like Facebook and Instagram.
↳Scraping contact details from Google Maps listings.
↳Collecting results from Google Search Engine Results Pages (SERPs).
↳Performing web searches and extracting content from top URLs for RAG (Retrieval-Augmented Generation).
↳Automating data collection from e-commerce sites and other websites.
10

Alternatives

⚡Top VS:
VSbrightdata-mcp★2.7k→VSScrapling★89.2k→VSPyScrappy★263→

Featured in these lists

  • Best MCP Servers for Browser Automation

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs

Most discussed open issues

  • #184 Add support for exposing a subset of input schema attributes, with the option to fetch all attributes when needed14 comments · 2025-07-23
  • #1551 ci: Release bump job fails on flaky reviewer request7 comments · 2026-10-13
  • #1266 [Bug]: Input-schema value constraints are stripped from Actor tool schemas5 comments · 2026-08-17
  • #1086 Add your HVTrust badge to the README?5 comments · 2026-07-13
  • #580 Use reduced store search response for search-actors tool4 comments · 2026-03-21

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

VS
crw
★1.2k
→
brightdata-mcp logo
brightdata-mcp★ 2.7k
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
VSCompare→
Scrapling logo
Scrapling★ 89.2k
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
VSCompare→
PyScrappy logo
PyScrappy★ 263
Python web scraping toolkit and MCP server that gives AI agents clean, structured web data from any URL or built-in scrapers.
VSCompare→
crw logo
crw★ 1.2k
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.
VSCompare→
wigolo logo
wigolo★ 5.5k
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
VSCompare→
oya-browser logo
oya-browser★ 351
The browser control plane for AI agents. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and your own Chrome, with persistent personas, CAPTCHA and MFA handling, and live human takeover.
VSCompare→
cloakbrowser-mcp logo
cloakbrowser-mcp★ 169
⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
VSCompare→
steel-mcp-server logo
steel-mcp-server★ 58
MCP Server for interacting with a Steel web browser
VSCompare→
See all alternatives →
07
Compatibility
08Quick start
09Use cases
10Alternatives
apify /
apify-mcp-server
↗

Hosted MCP gateway to thousands of ready-made Apify scrapers

12.6k415MIT
Last commit1d ago
StatusActive
CategoryBrowser Automation
Contributors51
Latest releasev0.18.4
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit