Skip to main content

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.

Cursor is an AI-powered code editor. The Cursor MCP server lets you launch and manage cloud agents that work on your GitHub repositories using natural language.

​
What Can It Do?

  • Launch cloud agents to work on GitHub repositories
  • Monitor agent status and view conversation history
  • Send follow-up instructions to running agents
  • Stop and delete agents when done

​
Where to Use It

Add Cursor as a tool to any agent. The agent can then interact with Cursor conversationally, choosing the right actions based on context. To add an MCP tool to your agent:
  1. Open your agent’s configuration
  2. Click Add tools → Connect an app with MCP
  3. Search for the integration and select it
  4. Authenticate with your account
You can control which tools your agent has access to. After adding an integration, click on it to enable or disable specific tools based on what your agent needs.

​
In Workflows (Via Agent Node)

For automated pipelines, use an Agent Node with Cursor 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.
To create a custom MCP node:
  1. Go to your node library and search for the integration
  2. Click Create a node with AI
  3. Describe the specific action you want (e.g., “Launch an agent to fix the login bug”)
  4. 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

ToolDescription
List AgentsList all cloud agents for the authenticated user
Launch AgentLaunch a new cloud agent to work on a GitHub repository
Get AgentGet a cloud agent’s status and results
Get Agent ConversationGet a cloud agent’s conversation history
Add FollowupSend a follow-up instruction to a running cloud agent
Stop AgentStop a running cloud agent
Delete AgentPermanently delete a cloud agent
List ModelsList available LLM models for cloud agents
List RepositoriesList accessible GitHub repositories

​
Example Prompts

Use these with your agent or in the Agent Node: Launch an agent: 
Launch a Cursor agent to refactor the auth module in my-repo
Check status: 
What's the status of my running Cursor agents?
Send follow-up: 
Tell my Cursor agent to also update the tests

​
Troubleshooting

IssueSolution
Authentication failedVerify your Cursor credentials and that you have the required permissions
Tool not availableVerify the tool is enabled in your agent’s MCP configuration
Unexpected resultsThe agent may chain multiple tools together. Review the agent’s reasoning to understand its approach.
Agents are smart enough to chain multiple API calls together. If results seem off, check the agent’s step-by-step reasoning.

​
Need Help?

Use this integration directly in Claude or Cursor. Connect remotely via the Cursor MCP server using your Gumloop credentials.