LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Toolofficial publisher

Actors Apify comme outils

Tool : A precise action the AI can call · requires apify

7,000+ scrapers and automations callable by an agent.

The largest scraping catalogue available; each actor carries its own trust level.

Overall score
6.5 /10
Security: one caveat, see the card
Utility
7.0
Reliability
6.0
Security
One caveat
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Finding and running web scraping or automation scripts usually requires technical skills and setup time. Apify MCP Server solves this by exposing more than 7,000 ready-to-use automations, called Actors, directly to an AI agent via the MCP protocol.

In practice, the agent can search for an Actor in the Apify Store catalogue, inspect its input and output parameters, and run it on demand without any prior configuration. Results are retrievable through dedicated tools, with an immediate preview and the option to fetch the full output when needed.

This service is aimed at developers and teams building their own AI agents who want to give them web data collection capabilities without developing those components themselves. It is compatible with Claude Desktop, Cursor, VS Code via GitHub Copilot, and any MCP-compatible client.

It is not suited for users looking for a simple conversational interface: for that use case, Apify offers Apify AI directly in its console. Actors requiring full permissions or operating on a subscription basis are also excluded from the MCP server for security and compatibility reasons.

What it offers

  • ·Search for Actors in the Apify Store catalogue directly from the AI agent, without leaving the working environment.
  • ·Inspect Actor details, including input and output schemas and README, before running them.
  • ·Run an Actor on demand and retrieve its results, with an immediate preview and access to the full output. (paid)
  • ·Access stored data: datasets, key-value stores, and run logs. (paid)
  • ·Create, update, and publish reusable Actor tasks to automate recurring configurations. (paid)
  • ·Search and read Apify documentation directly from the agent, usable without authentication.
  • ·Browse and extract web data via the RAG Web Browser Actor, included by default.
  • ·Agentic payments allowing an agent to fund its own runs through third-party services like AGI or Skyfire, without a pre-configured Apify token. (paid)

In practice

Price
Freemium
Commercial use
Commercial use: yes
Available on
api, mcp
Host
apify
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Capabilities
readswritesexecutesnetwork
Your data
Data with third parties
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 January 2024

How to install Actors Apify comme outils

1. Create an Apify account at apify.com and retrieve your API token from the "API & Integrations" section of the console. 2. Keep this token secure: it authorises Actor execution on your behalf and must not be shared. 3. In your MCP client (Claude Desktop, Cursor, VS Code...), add https://mcp.apify.com as the MCP server URL. 4. On first connection, authenticate via OAuth in your browser, or add the Authorization: Bearer <YOUR_TOKEN> header in the configuration. 5. Optionally, refine the exposed tools by appending the ?tools= parameter to the URL, or use the visual configurator at mcp.apify.com to generate the appropriate configuration.
npx @apify/actors-mcp-server

Official documentation ↗

In the same category

Whole category Feed (memory, context) →