Apify MCP. Run scrapers and analyze data without leaving your agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Apify MCP Server manages your web scraping and automation pipelines. You can list actors, trigger runs, and manage datasets directly from your AI client.
Use `list_actors` to see available scrapers, `run_actor` to start a job, and `get_dataset_results` to pull the structured data for analysis.
What your AI agents can do
Get dataset results
Retrieves the actual records (items) from a specified Apify dataset.
Get run details
Fetches detailed logs and status information for a specific, past or current actor run.
List actor runs
Lists the most recent execution attempts for your configured web scrapers.
Use list_actors to see all the scrapers (actors) you have set up in your Apify account.
Run run_actor to start a new web scraping or automation job using a specific actor.
Call get_dataset_results to retrieve the structured data items from a specific dataset ID.
Use get_run_details to get deep details and logs about a specific, completed, or running job run.
Call list_datasets to get a list of every dataset you've stored data into.
Use list_actor_tasks to see and manage the reusable settings for your scrapers.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Apify MCP Server: 7 Tools for Web Data Management
Use these tools to manage the full web data lifecycle: list actors, trigger runs, track status, and pull structured results.
019dd0b9get dataset results
Retrieves the actual records (items) from a specified Apify dataset.
019dd0b9get run details
Fetches detailed logs and status information for a specific, past or current actor run.
019dd0b9list actor runs
Lists the most recent execution attempts for your configured web scrapers.
019dd0b9list actor tasks
Shows the saved, reusable input configurations for your scrapers.
019dd0b9list actors
Lists all the scrapers (actors) configured in your Apify account.
019dd0b9list datasets
Retrieves a list of all the data storage containers in your account.
019dd0b9run actor
Starts a new instance of a web scraping or automation job using a selected actor.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Apify, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're connecting your Apify account to your AI client. You can run scraping and automation pipelines and manage all your data from one place. list_actors shows you every scraper (actor) you've got set up. You can use run_actor to kick off a scraping or automation job with a specific actor.
To pull the structured data records, you call get_dataset_results with a specific dataset ID. You can check the history and status of any job run using list_actor_runs or get deep logs and status details for a particular run with get_run_details. You can see every data container you've stored data into by calling list_datasets.
To manage your scrapers' reusable settings, you'll use list_actor_tasks.
How Apify MCP Works
- 1 First, use
list_actorsto see all the scrapers available in your account. - 2 Next, use
run_actorto start a job, providing the necessary inputs and the target actor ID. - 3 Finally, use
get_dataset_resultswith the resulting dataset ID to pull the structured data for analysis.
The bottom line is, you get the full web data lifecycle managed—from listing the scraper to getting the final data points.
Who Is Apify MCP For?
The data scientist who needs to move beyond simple manual scraping. The operations engineer who can't trust a process that requires constant dashboard clicking. Anyone who needs to treat web data extraction like a programmable, auditable workflow.
They use get_dataset_results to quickly pull scraped data into the agent for trend analysis or pattern detection, instead of exporting CSVs.
They use list_actors and run_actor to build and test scraping pipelines, monitoring execution health via list_actor_runs.
They use this server to get an instant overview of data collection tasks and results, proving data collection feasibility without needing to write code.
What Changes When You Connect
- See structured data immediately. Instead of manually downloading and processing CSVs, use
get_dataset_resultsto pull records directly into your agent for instant analysis. - Manage the whole pipeline. Trigger scrapers and track their status using
run_actorandlist_actor_runs. You don't have to jump between the Apify UI and your chat. - Debug complex jobs easily. If a run fails, don't guess. Use
get_run_detailsto pull detailed logs and metadata for the exact failure point. - Audit your data sources. Use
list_datasetsto see every dataset you've created. Know exactly where your collected web data lives. - Reuse scraper settings. Don't reconfigure inputs every time. Check
list_actor_tasksto see and reuse saved scraper settings. - Discover available tools. Use
list_actorsto get a clean list of every scraper you can run, saving time finding the right actor ID.
Real-World Use Cases
Tracking Competitor Pricing Changes
A market analyst needs to see how a competitor's pricing changed last week. They ask their agent to list the relevant actors via list_actors, trigger a run with updated selectors using run_actor, and then use get_dataset_results to get the structured data for a time-series graph.
Auditing a Failed Data Collection Run
An automation engineer notices a dataset is incomplete. They first call list_actor_runs to find the ID of the bad run, then use get_run_details to pull the logs. This pinpoints whether the failure was due to a bad selector or a rate limit.
Setting up a New Data Source
A researcher wants to scrape a new niche website. They use list_actors to find a base template, use list_actor_tasks to save the specific site settings, and finally use run_actor to execute the new scraper against the target site.
Creating a Data Report from Existing Scrapes
A product manager needs to summarize all user reviews collected over the last month. They use list_datasets to confirm the dataset name, then call get_dataset_results to pull the 25 records into the agent for a summary report.
The Tradeoffs
Manually remembering IDs
Trying to remember the exact dataset ID (ds_10293) and the run ID (run_88231) to manually paste into the chat. This is tedious and prone to copy/paste errors.
→
First, call list_datasets to get the correct dataset ID. Then, use list_actor_runs to get the run ID. Your agent handles the IDs automatically.
Over-relying on the UI
Going to the Apify website, navigating through three separate tabs (Actors, Runs, Datasets) just to get a single list of all available scrapers.
→
Just ask your agent to run list_actors. It pulls the list instantly, saving you the browser clicks and tab switching.
Confusing run status
Seeing a run status is 'pending' but not knowing if the job is still running, waiting for resources, or if it failed silently. This leads to waiting indefinitely.
→
Use get_run_details. This tool gives you the specific logs and status context, telling you exactly why the job is stuck or if it succeeded.
When It Fits, When It Doesn't
Use this server if your workflow involves web scraping, data collection, or automation. You need to go from a web source to a structured dataset and then analyze it within your agent environment. Don't use this if you only need to send an email or manage a calendar event—use a dedicated messaging or calendar tool instead. If you only need to list data sources, list_datasets is enough. If you need to run the scraper, you must use run_actor and then check results with get_dataset_results.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Apify. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Web scraping data shouldn't require jumping between dashboards and tabs.
Today, getting structured data means logging into Apify, finding the correct actor, configuring the input parameters, hitting 'Run,' waiting for the status to change, and finally navigating to the dataset tab to download the results. It's a multi-step process full of clicks and copy-pasting.
With the Apify MCP Server, you just ask your agent to scrape the data. The agent handles listing the correct actor, running the job via `run_actor`, and then fetching the results using `get_dataset_results`. You get the structured data right in your conversation.
Get Apify MCP Server: Manage your data flow with `run_actor`.
Before this server, triggering a scraper meant opening a new tab, pasting API keys, and manually starting the job. Debugging meant clicking through multiple run IDs and status pages.
Now, you simply instruct your agent to run the scraper. The agent handles the execution via `run_actor`, monitors the job, and reports the status. It's all one conversation.
Common Questions About Apify MCP
How do I list all scrapers using the `list_actors` tool? +
Use list_actors to get a list of all available scrapers in your Apify account. This is the first step if you don't know which actor to run.
What is the difference between `get_dataset_results` and `list_datasets`? +
list_datasets just gives you the names and IDs of your data storage containers. get_dataset_results fetches the actual rows and data items from a specific dataset ID.
How do I check the status of a recent scraping job using `list_actor_runs`? +
Run list_actor_runs to see a history of recent jobs. If you need deep logs or the exact status, use get_run_details with the specific run ID.
Can I run an actor without knowing its ID? (using `run_actor`) +
No. The run_actor tool requires the specific actor ID to know which scraper to execute. Always start by using list_actors to find the correct ID.
What tool should I use to save my current scraper setup? (using `list_actor_tasks`) +
Use list_actor_tasks to view and manage saved input configurations. This lets you reuse complex settings for your scrapers without re-entering them.
How do I check the execution history of a specific scraper run using `get_run_details`? +
You use get_run_details by providing the unique run ID. This gives you the full execution history, including logs and metadata. This is essential for debugging complex automations or verifying specific data points.
What happens if I need to reuse a saved scraper configuration? (using `list_actor_tasks` and `run_actor`) +
First, use list_actor_tasks to see your saved configurations. Then, pass the task ID to run_actor to trigger the run. This saves you from re-entering complex settings.
How do I see all the data I've collected and where is it stored? (using `list_datasets` and `get_dataset_results`) +
Start by calling list_datasets to see all your saved data containers. Once you find the correct dataset ID, use get_dataset_results to fetch the actual records for analysis.
Can I provide input parameters when running an actor? +
Yes! Use the run_actor tool and provide the optional input JSON object to configure specific scraper settings for that run.
How do I see the items collected in a dataset? +
Run the get_dataset_results query with your Dataset ID. The agent will retrieve the data records, which you can then ask the AI to summarize or analyze.
Is it possible to check the status of a specific actor run? +
Absolutely. Use the get_run_details tool and provide the Run ID. Your agent will retrieve the status (RUNNING, SUCCEEDED, FAILED) and metadata for that specific execution.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Browserbase
Cloud browser infrastructure for AI agents — create, control, and manage headless Chromium sessions via CDP for automated web interaction.
Runlayer
AI enterprise control plane: manage MCP servers, skills, agents, and security policies via agents.
LangSmith (LLM Observability & Hub)
Monitor LLM apps via LangSmith — track traces, audit prompt templates, and manage evaluation datasets.
You might also like
Bookingmood
Manage your rental bookings via Bookingmood — track rentals, manage calendars, and handle guest contacts directly from any AI agent.
Smartsheet
Empower your AI to read Smartsheet rows, list workspaces, and manage your spreadsheets effortlessly from your code editor.
Truto Unified Calendar
Empower your AI agent with a universal API to read, schedule, and sync events seamlessly across Google, Outlook, and other major calendar providers.