Skip to main content
Gumloop exposes a remote Model Context Protocol (MCP) server that lets any compatible AI client manage your workflows, agents, sessions, skills, and more. Connect to the Gumloop MCP server natively in Claude, Cursor, and other clients, or use mcp-remote for clients that don’t yet support remote MCP. 
https://mcp.gumloop.com/gumloop/mcp
You’ll need a Gumloop API key. Get one from Settings > Credentials. 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: 
https://mcp.gumloop.com/gumloop/mcp

​
Cursor

  1. Open Cursor Settings (Cmd/Ctrl + Shift + J)
  2. Go to MCP and click Add new MCP server
  3. Select Type: SSE and enter the server URL:
https://mcp.gumloop.com/gumloop/mcp

​
VS Code

Add the following to your .vscode/mcp.json: 
{
  "mcpServers": {
    "gumloop": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.gumloop.com/gumloop/mcp"]
    }
  }
}

​
Windsurf

  1. Open Windsurf settings (Cmd/Ctrl + ,)
  2. Scroll to Cascade > MCP servers
  3. Select Add Server > Add custom server
  4. Add:
{
  "mcpServers": {
    "gumloop": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.gumloop.com/gumloop/mcp"]
    }
  }
}

​
Gumloop CLI

You can also explore and call tools from your terminal: 
gumloop mcp list                                    # List connected servers
gumloop mcp tools gumloop                           # Browse available tools
gumloop mcp call gumloop list_agents --args-json '{}' # Call a tool
See the CLI MCP docs for the full reference.

​
Available Tools

The Gumloop MCP server exposes 35 tools across these categories:

​
Workflow Management

ToolDescription
list_saved_flowsList saved flows/items in your account for a specific user or project
list_workbooksList workbooks and their associated saved flows with nested flow information
start_flow_runStart/trigger flow execution with optional input parameters
get_run_detailsRetrieve detailed flow run information including state, outputs, logs, and timestamps
get_run_historyRetrieve automation run history for workbooks or saved items with execution details

​
Agent Management

ToolDescription
list_agentsList agents in your account, with optional search and workspace filtering
get_agentFetch a single agent’s configuration by its ID
create_agentCreate a new agent with a name, model, and optional configuration
update_agentUpdate an existing agent’s metadata or configuration
list_modelsList the model groups available to agents

​
Agent Sessions

ToolDescription
start_agentSend a message to an agent and start an asynchronous interaction
get_agent_statusPoll the status of an agent interaction and retrieve the response when completed
create_agent_sessionStart a session on an agent and return the completed response
get_sessionFetch the state and result of an agent session by ID
send_session_messageSend a follow-up message to an existing session and return the completed response
cancel_sessionCancel an in-progress agent session

​
Skills

ToolDescription
list_skillsList skills in your account, with optional search, filtering, and pagination
create_skillCreate a skill from one or more files stored in your workspace
update_skillReplace a skill’s files with files stored in your workspace
delete_skillDelete a skill from your account
download_skillGet a download URL for a skill archive

​
Artifacts

ToolDescription
list_agent_artifactsList the artifacts an agent has produced, with optional session filtering and pagination
download_artifactGet a download URL for an agent artifact

​
Teams

ToolDescription
list_teamsList the teams (workspaces) the authenticated user belongs to

​
MCP Server Management

ToolDescription
list_mcp_serversList the MCP servers connected to your account
get_mcp_serverFetch a single connected MCP server’s configuration by ID
list_mcp_server_toolsList the tools exposed by a connected MCP server
call_mcp_toolExecute a single tool on a connected MCP server
list_mcp_resourcesList the resources exposed by a connected MCP server
read_mcp_resourceRead the contents of a resource from a connected MCP server by URI
list_mcp_promptsList the prompts exposed by a connected MCP server
get_mcp_promptGet a rendered prompt from a connected MCP server, with optional arguments

​
Documentation & Admin

ToolDescription
search_documentationSearch Gumloop documentation using semantic and keyword search with filtering options
ask_gummieAsk questions and get AI-powered answers from Gumloop documentation with citations
get_audit_logsRetrieve organization audit logs with event details and filtering by time period (admin only)

​
Example Prompts

Once connected, try these with your AI client: 
Show me all my saved flows

Start the "Daily Report" flow with input parameter date set to today

Create a new agent called "Research Assistant" using the GPT-4o model

Start a session with my Research Assistant agent and ask it to summarize the latest quarterly report

What MCP servers are connected to my account?

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?