Gumloop is an AI automation platform for building agents and workflows. The Gumloop MCP server lets you manage flows, trigger runs, monitor executions, interact with agents, and search documentation using natural language.
What Can It Do?
- List and manage saved flows and workbooks in your account
- Trigger flow runs with optional input parameters
- Monitor run status and retrieve detailed execution results
- Start agent interactions and poll for responses asynchronously
- Search documentation and get AI-powered answers
- Access audit logs for organization-level activity tracking
Where to Use It
In Agents (Recommended)
Add Gumloop as a tool to any agent. The agent can then manage your automations 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
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 Gumloop 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:
- Go to your node library and search for the integration
- Click Create a node with AI
- Describe the specific action you want (e.g., “Start my daily report flow”)
- 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.
Workflow Management
| Tool | Description |
|---|
| List Saved Flows | List saved flows/items in your account for a specific user or project |
| List Workbooks | List workbooks and their associated saved flows with nested flow information |
| Start Flow Run | Trigger a flow execution with optional input parameters |
| Get Run Details | Retrieve detailed flow run information including state, outputs, logs, and timestamps |
| Get Run History | Retrieve automation run history for workbooks or saved items with execution details |
Agent Interaction
| Tool | Description |
|---|
| Start Agent | Send a message to a Gumloop agent and start an asynchronous interaction |
| Get Agent Status | Poll the status of an agent interaction and retrieve the agent’s response when completed |
Documentation & Admin
| Tool | Description |
|---|
| Search Documentation | Search Gumloop documentation using semantic and keyword search with filtering options |
| Ask Gummie | Ask questions and get AI-powered answers from Gumloop documentation with citations |
| Get Audit Logs | Retrieve organization audit logs with event details and filtering by time period (admin only) |
Example Prompts
Use these with your agent or in the Agent Node:
List flows:
Show me all my saved flows
Trigger a run:
Start the "Daily Report" flow with input parameter date set to today
Check run status:
What's the status of my latest flow run?
Start an agent conversation:
Send a message to my support agent asking "How do I reset my password?"
Check agent response:
Check if the support agent has responded to my last message
Search docs:
Search the Gumloop documentation for how to set up webhooks
Ask Gummie:
How do I configure a Slack trigger for my workflow?
View audit logs:
Show me the organization audit logs from the past week
Troubleshooting
| Issue | Solution |
|---|
| Agent not finding the right data | Specify flow names or project IDs explicitly |
| Action not completing | Check that you’ve authenticated with Gumloop |
| Unexpected results | The agent may chain multiple tools (e.g., listing flows first, then triggering a run). Review the agent’s reasoning to understand its approach. |
| Tool not available | Verify the tool is enabled in your agent’s MCP configuration |
Agents are smart enough to chain multiple API calls together. For example, asking “Run my latest flow and show me the results” will list flows, trigger a run, and poll for completion. 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 Gumloop MCP server using your Gumloop credentials.