mcp-remote for clients that don’t yet support remote MCP.
You’ll need a Gumloop API key. Get one from Connectors page. The server handles OAuth automatically: you’ll be prompted to sign in and authorize access the first time you connect.
Setup
Claude
Navigate to Settings > Connectors and add a new MCP integration with the URL:Cursor
- Open Cursor Settings (Cmd/Ctrl + Shift + J)
- Go to MCP and click Add new MCP server
- Select Type: SSE and enter the server URL:
VS Code
Add the following to your.vscode/mcp.json:
Windsurf
- Open Windsurf settings (Cmd/Ctrl + ,)
- Scroll to Cascade > MCP servers
- Select Add Server > Add custom server
- Add:
Gumloop CLI
You can also explore and call tools from your terminal:Available Tools
The Gumloop MCP server exposes 45 tools across these categories:Agent Management
Agent Sessions
Skills
Artifacts
Teams
MCP Server Management
Company Brain
Documentation & Admin
Data Exports
Use these two together to pull your organization’s agent and usage data into an MCP client: call
export_data with a data_type (workflows, agents, agent_interactions, credit_logs, or gumstack), a date range, and the columns you want, then poll get_export_status with the returned data_export_id until it reports COMPLETED and request the download URL.
The aggregated charts on the Organization Insights dashboard (overview totals, model usage, leaderboards, skill adoption, artifact analytics) aren’t available over MCP or the REST API. Use data exports for the underlying rows.
Workflow Management
Example Prompts
Once connected, try these with your AI client:Related Resources
Gumloop MCP Integration
Full tool reference and usage examples.
API Reference
Programmatically manage MCP servers and call tools via the REST API.
CLI Reference
Explore and call MCP tools from your terminal.
Custom MCP Servers
Connect your own MCP servers to Gumloop.
Need Help?
- Agents documentation for using MCP tools with agents
- Need help? Reach out to us
- Browse our Knowledge Base for common questions
