MCP Servers · apify

apify-mcp-server

Apify MCP Server is a TypeScript-based Model Context Protocol server that integrates AI agents with Apify's web scraping and automation platform. It enables agents to discover and execute thousands of pre-built scrapers and crawlers for data extraction from websites, with support for both hosted (HTTPS) and local (stdio) deployment.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/apify/apify-mcp-server

1.7k

GitHub stars

186

Forks

TypeScript

Primary language

MIT

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	apify/apify-mcp-server
Owner	apify
Primary language	TypeScript
License	MIT — OSI-approved
Stars	1.7k
Forks	186
Open issues	116
Latest release	v0.11.5 (2026-07-02)
Last updated	2026-07-07
Source	https://github.com/apify/apify-mcp-server

What apify-mcp-server is

MCP server written in TypeScript that bridges AI agents to the Apify Actor ecosystem via the Model Context Protocol. Provides tool discovery, Actor execution, OAuth authentication, and experimental agentic payment integrations (x402, Skyfire). Supports multiple transport mechanisms: streamable HTTP for hosted deployment and stdio for local integration.

Quickstart

Get the apify-mcp-server source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/apify/apify-mcp-server.git2cd apify-mcp-server3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

AI-Driven Web Data Extraction

Integrate AI agents with production-ready scrapers for social media, search engines, e-commerce, and maps to automate data collection workflows without building custom extraction logic.

Autonomous Agent Tooling

Enable Claude, ChatGPT, and other AI assistants to autonomously discover and invoke Apify Actors as tools within agentic workflows, reducing dependency on manual API integration.

Multi-Platform Automation

Support agents running in diverse environments (Claude Desktop, VS Code, Cursor, Claude.ai) via a single hosted MCP endpoint with OAuth, eliminating per-client configuration complexity.

Implementation considerations

Requires an Apify account and API token (or OAuth setup) for authentication; agentic payment methods (x402, Skyfire) are experimental and require additional wallet/account setup.
Hosted deployment at mcp.apify.com is recommended for feature completeness (output schema inference); local stdio deployment via npm has feature parity gaps.
Clients must support MCP protocol; feature support (dynamic tool discovery, output schema inference) varies across Claude Desktop, VS Code, Cursor, and other clients—test integration path before production.
Actor execution costs vary; agentic payment prepayment model requires agents to manage prepaid balances, adding complexity to autonomous workflows.
Telemetry is enabled by default; review privacy policy implications if data handling policies apply to your organization.

When to avoid it — and what to weigh

Custom or Proprietary Scraping Logic Required — If your data extraction needs are highly specialized or domain-specific and Apify Store's pre-built Actors do not cover your use case, this server adds a layer without solving the underlying gap.
Offline-Only Deployment — Apify MCP Server requires connectivity to Apify's infrastructure. If your deployment environment is air-gapped or offline-first, this solution is unsuitable.
Vendor Lock-in Constraints — Organizations with strict policies against external SaaS dependencies should evaluate whether reliance on Apify's hosted platform and Actor ecosystem aligns with strategic requirements.
Real-Time Bidirectional Communication — MCP is designed for request-response patterns. If you need persistent bidirectional streaming or real-time event-driven architecture, evaluate alternative messaging patterns.

License & commercial use

Licensed under MIT (MIT License), a permissive open-source license. Permits commercial use, modification, and distribution with minimal restrictions; requires license and copyright notice retention.

MIT license permits commercial use without additional permissions. However, commercial usage depends on Apify's terms of service for the platform and Actor ecosystem. Running Apify Actors incurs usage costs and is subject to Apify's commercial terms. Verify Apify's ToS and licensing for Actors in the Store to ensure compliance for commercial deployments.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Strong
License clarity	Clear
Deployment complexity	Low
DEV.co fit	Strong
Assessment confidence	High

Security considerations

Server handles authentication via OAuth and Bearer tokens (API tokens); ensure token rotation and storage practices follow organizational security baselines. Data extraction from external websites may expose sensitive information; review compliance and data handling policies for web scraping. Telemetry is enabled by default; privacy policy should be reviewed before deployment. No information on input validation, injection prevention, or audit logging—requires vendor documentation review.

Alternatives to consider

Custom REST API Integration with Apify SDK

If you need tighter control over Actor orchestration and cost management without the MCP abstraction, build a direct REST client using @apify/client SDK and integrate with your agent framework natively.

Bright Data or Scrapingbee

Alternative web scraping APIs with agent-friendly SDKs and different pricing models; evaluate if Apify's Actor ecosystem and MCP integration do not align with cost or feature requirements.

Langchain Web Tools + Firecrawl/Jina

For lightweight agentic web scraping without external tooling integration, use Langchain's built-in web tools or dedicated scraping APIs (Firecrawl, Jina); simpler for agents that do not require deep Actor ecosystem access.

Software development agency

Build on apify-mcp-server with DEV.co software developers

Deploy Apify MCP Server to unlock autonomous data extraction for your Claude, ChatGPT, or custom agents. Start with the hosted endpoint or deploy locally—no additional setup required.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

mcpc firecrawl-mcp-server mcp

Related on DEV.co

Explore the category and the services that help you build with it.

MCP Servers AI Application Development Web Application Development API Development Talk to DEV.co

apify-mcp-server FAQ

Can I run Apify MCP Server locally without internet?

No. The server requires connectivity to Apify's infrastructure to discover and execute Actors. Local stdio deployment is supported, but the backend is cloud-based.

Which clients support the latest MCP features like output schema inference?

Schema inference is available only on the hosted endpoint (https://mcp.apify.com). Local stdio deployment does not support this feature. Client support varies; Claude Desktop, VS Code, and Cursor are tested; refer to mcp.apify.com configuration for latest compatibility.

Do I need an Apify account and API token to use this?

For standard deployment, yes—an Apify account and API token are required. Experimental agentic payment methods (x402, Skyfire) allow token-less execution but require additional wallet setup and are not yet production-grade.

What are the costs associated with using Apify MCP Server?

The server itself is free and open-source. Actor execution costs depend on Apify's pricing model (varies by Actor and compute). Review Apify Store pricing and your account tier before deploying agents with autonomous execution.

Work with a software development agency

Need help beyond evaluating apify-mcp-server? DEV.co is a software development agency offering software development services and web development for teams of every size. Our software developers and web developers build custom software, web applications, APIs, and mcp servers integrations — and maintain them long-term.

Integrate Web Scraping into Your AI Agents

Deploy Apify MCP Server to unlock autonomous data extraction for your Claude, ChatGPT, or custom agents. Start with the hosted endpoint or deploy locally—no additional setup required.

Talk to DEV.co Schedule a Consultation