How to Use the Apify MCP in Claude
Run Apify web scrapers and pull structured datasets directly into your Claude Desktop chat window.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Apify MCP to Claude Desktop
Create your Vinkius account to connect Apify to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Trigger and track Apify actors from Claude Desktop
The `run_actor` tool kicks off any Apify scraper asynchronously right from your chat prompt. You pass the actor ID and your custom JSON input parameters directly to the tool, which instantly returns a run ID. To avoid sitting around waiting for massive crawls, you can use `get_run` to poll the status of your active scraper while you continue chatting about other things. If you're running short, quick tasks that take less than five minutes, `run_actor_sync` blocks the execution and returns the finished run object immediately. When a scraper goes rogue or eats up too many resources, you can halt it instantly by calling `abort_run` to save your budget.
Pull clean dataset JSON into your Claude Desktop window
The `get_dataset_items` tool fetches structured JSON data from your completed scraper runs directly into your active conversation. You feed it the dataset ID, and the tool pulls the raw scraped records, supporting pagination parameters like limit and offset to handle massive data payloads. For unstructured or binary outputs like screenshots and configuration files, `get_key_value_store` retrieves specific items using keys like OUTPUT or SCREENSHOT. This lets your agent analyze actual page captures and raw files without leaving the chat interface.
Control your scraping infrastructure via this MCP Server
The `list_actors` tool queries your Apify account to show every scraper you own or have saved from the store. This makes it easy to find the exact actor ID you need before launching a new crawl. You can also inspect your event-driven setups with `list_webhooks` to see which URLs get notified when runs succeed or fail. To keep tabs on your budget, `get_account_limits` checks your compute unit usage and subscription constraints before you trigger heavy jobs. If you're running a dynamic crawl, you can feed new URLs on the fly using `push_to_queue` to expand your scraper's target list during execution.
Set up Apify MCP in Claude Web or Desktop
- 1
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
- 2
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcpReplace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials. - 3
Start a conversation
Open a new chat. The Apify MCP tools are available immediately — no restart needed.
Endpoint URL
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp No configuration file needed — paste the URL directly in the Claude web interface.
Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.
Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about Apify MCP in Claude Desktop
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Apify MCP today
We host it, we monitor it, we maintain it. You just paste one token.