Skip to main content

Gumloop

Gumloop's hosted MCP server for managing agents, sessions, skills, and workflows

Tools

45 available tools

Search the tool definitions captured from the MCP server. The live list can vary with version, deployment, and credentials.

45 tools found.

  • List agents

    Tool name: list_agents

    List agents in your Gumloop account, with optional search and workspace filtering.

  • Get agent

    Tool name: get_agent

    Fetch a single Gumloop agent's configuration by its ID.

  • Ask gummie

    Tool name: ask_gummie

    Ask questions and get AI-powered answers from Gumloop documentation.

  • Attach agent MCP server

    Tool name: attach_agent_mcp_server

    Attach an MCP server (connector) to a Gumloop agent, or update its configuration if already attached.

  • Attach agent skills

    Tool name: attach_agent_skills

    Attach one or more existing skills to a Gumloop agent.

  • Call MCP tool

    Tool name: call_mcp_tool

    Execute a single tool on a connected MCP server.

  • Cancel session

    Tool name: cancel_session

    Cancel an in-progress Gumloop agent session.

  • Create agent

    Tool name: create_agent

    Create a new Gumloop agent with a name, model, and optional configuration.

  • Create agent session

    Tool name: create_agent_session

    Start a session on a Gumloop agent and return the completed (non-streamed) response.

  • Create skill

    Tool name: create_skill

    Create a skill from one or more files stored in your Gumloop workspace.

  • Delete skill

    Tool name: delete_skill

    Delete a skill from your Gumloop account.

  • Detach agent MCP server

    Tool name: detach_agent_mcp_server

    Detach an MCP server (connector) from a Gumloop agent.

  • Detach agent skills

    Tool name: detach_agent_skills

    Detach one or more skills from a Gumloop agent.

  • Download artifact

    Tool name: download_artifact

    Get a download URL for an agent artifact.

  • Download skill

    Tool name: download_skill

    Get a download URL for a skill archive.

  • Export data

    Tool name: export_data

    Create an organization data export and return a data_export_id to poll with get_export_status.

  • Get agent status

    Tool name: get_agent_status

    Poll the status of an agent interaction started with start_agent.

  • Get agent version

    Tool name: get_agent_version

    Fetch an immutable Gumloop agent version and its configuration.

  • Get audit logs

    Tool name: get_audit_logs

    Retrieve audit logs for an organization within a specified time period.

  • Get export status

    Tool name: get_export_status

    Poll a data export's status and optionally get a signed download URL for the completed CSV.

  • Get MCP prompt

    Tool name: get_mcp_prompt

    Get a rendered prompt from a connected MCP server, with optional arguments.

  • Get MCP server

    Tool name: get_mcp_server

    Fetch a single connected MCP server's configuration by ID.

  • Get run details

    Tool name: get_run_details

    Retrieve details of a specific flow run, including state, outputs, and logs.

  • Get run history

    Tool name: get_run_history

    Retrieve automation run history for workbooks or saved items.

  • Get session

    Tool name: get_session

    Fetch the state and result of a Gumloop agent session by ID.

  • List agent artifacts

    Tool name: list_agent_artifacts

    List the artifacts an agent has produced, with optional session filtering and pagination.

  • List agent sessions

    Tool name: list_agent_sessions

    List an agent's sessions, with search, filters, sort, and pagination.

  • List agent versions

    Tool name: list_agent_versions

    List immutable versions of a Gumloop agent.

  • List MCP prompts

    Tool name: list_mcp_prompts

    List the prompts exposed by a connected MCP server.

  • List MCP resources

    Tool name: list_mcp_resources

    List the resources exposed by a connected MCP server.

  • List MCP server tools

    Tool name: list_mcp_server_tools

    List the tools exposed by a connected MCP server.

  • List MCP servers

    Tool name: list_mcp_servers

    List the MCP servers connected to your Gumloop account.

  • List models

    Tool name: list_models

    List the model groups available to Gumloop agents.

  • List saved flows

    Tool name: list_saved_flows

    List saved flows/items in your Gumloop account.

  • List skills

    Tool name: list_skills

    List skills in your Gumloop account, with optional search, filtering, and pagination.

  • List teams

    Tool name: list_teams

    List the teams (workspaces) the authenticated user belongs to.

  • List workbooks

    Tool name: list_workbooks

    List workbooks and their saved flows in your Gumloop account.

  • Read MCP resource

    Tool name: read_mcp_resource

    Read the contents of a resource from a connected MCP server by URI.

  • Search brain

    Tool name: search_brain

    Search your Company Brain's indexed knowledge sources for relevant content.

  • Search documentation

    Tool name: search_documentation

    Search Gumloop documentation using semantic and keyword search.

  • Send session message

    Tool name: send_session_message

    Send a follow-up message to an existing agent session and return the completed response.

  • Start agent

    Tool name: start_agent

    Send a message to a Gumloop agent and start an asynchronous interaction.

  • Start flow run

    Tool name: start_flow_run

    Start/trigger a flow run via API with optional input parameters.

  • Update agent

    Tool name: update_agent

    Update an existing Gumloop agent's metadata or configuration.

  • Update skill

    Tool name: update_skill

    Replace a skill's files with files stored in your Gumloop workspace.

Compatibility

Connect Gumloop to the clients your teams already use

27 AI clients can connect to Gumloop through Runlayer. Pick one for its setup steps and controls.

Why Runlayer

Why connect Gumloop through Runlayer?

One approved path

Approve Gumloop once and everyone gets it in the AI clients they already use. Runlayer holds the credentials, so nothing sits in client configuration.

Fine-grained policy

Control who can use each server, tool, and resource, and under which runtime conditions.

Runtime security

Scan tool inputs and outputs for prompt injection, credential exposure, PII, and data exfiltration, then alert, mask, or block.

Audit and observability

Trace every request across users, clients, tools, policies, scanner decisions, and downstream systems.

Frequently asked questions