Apify is a platform for web scraping, data extraction, and automation. The Apify MCP server lets you search the Apify Store, run Actors and saved tasks, monitor runs, and retrieve results using natural language.Documentation Index
Fetch the complete documentation index at: https://docs.gumloop.com/llms.txt
Use this file to discover all available pages before exploring further.
What Can It Do?
- Search and discover Actors in the Apify Store
- Run Actors synchronously or asynchronously with validated input
- Manage saved tasks for preconfigured Actor runs
- Monitor run status and retrieve logs
- Read dataset results from completed runs
Where to Use It
In Agents (Recommended)
Add Apify as a tool to any agent. The agent can then discover and run Actors conversationally, choosing the right actions based on context. To add an MCP tool to your agent:- Open your agent’s configuration
- Click Add tools → Connect an app with MCP
- Search for the integration and select it
- Authenticate with your account
In Workflows (Via Agent Node)
For automated pipelines, use an Agent Node with Apify tools. This gives you the flexibility of an agent within a deterministic workflow.As a Custom MCP Node
You can also create a standalone MCP node for a specific action. This generates a reusable node that performs one task, useful when you need the same operation repeatedly in workflows.- Go to your node library and search for the integration
- Click Create a node with AI
- Describe the specific action you want (e.g., “Run a web scraper Actor on a URL”)
- Test the node and save it for reuse
Custom MCP nodes are single-purpose by design. For tasks that require multiple steps or dynamic decision-making, use an agent instead.
Available Tools
Actor Discovery
| Tool | Description |
|---|---|
| Search Actors | Search runnable Actors in the Apify Store |
| Get Actor | Get Actor metadata and optionally its input schema |
| Validate Actor Input | Validate input for an Actor build before running |
Running Actors
| Tool | Description |
|---|---|
| Run Actor | Run an Actor synchronously or asynchronously |
| Get Run | Get Actor run status and metadata |
| Abort Run | Abort a running Actor run |
| Get Run Log | Get the log output from an Actor run |
Saved Tasks
| Tool | Description |
|---|---|
| List Tasks | List saved Apify Actor tasks |
| Get Task | Get a saved Apify Actor task |
| Run Task | Run a saved Actor task synchronously or asynchronously |
Results
| Tool | Description |
|---|---|
| Get Dataset Items | Get items from an Apify dataset |
The Gumloop-managed Apify key supports searching public Actors, reading public metadata, and running public limited-permission Actors synchronously. For full-permission Actors, async runs, saved tasks, run status, and dataset reads, connect your own Apify API key.
Example Prompts
Use these with your agent or in the Agent Node: Search for an Actor:Troubleshooting
| Issue | Solution |
|---|---|
| ”Full-permission Actor” error | Some Actors require your own Apify API key. Connect it in the integration settings |
| Run stuck or timing out | For long-running Actors, use async mode and check status with Get Run |
| Agent not finding the right Actor | Use specific keywords or the Actor’s full name from the Apify Store |
| Tool not available | Verify the tool is enabled in your agent’s MCP configuration |
Need Help?
- Agents documentation for setup and best practices
- Agent Node guide for workflow integration
- Gumloop Community for questions and examples
- Contact support@gumloop.com for assistance
Use this integration directly in Claude or Cursor. Connect remotely via the Apify MCP server using your Gumloop credentials.