Connection setup
Create a browser setup URL for a credentialed connection. Use a canonical `type` when known; otherwise pass `intent_text`. For hosted demo data with no credentials, use `install_demo_connection`.
MarcoPolo MCP lets agents securely query, correlate, analyze, and act on authorized data across databases, warehouses, cloud storage, and SaaS applications.
Create a browser setup URL for a credentialed connection. Use a canonical `type` when known; otherwise pass `intent_text`. For hosted demo data with no credentials, use `install_demo_connection`.
List visible Marcopolo connections ready in the execution workspace. Returned names are valid `connection_name` values for `data_query`. Capabilities and workspace paths describe supported workspace commands.
Run a bounded governed query against a visible connection. Use this tool in generated code that re-queries live data at view or load time: Remote Artifacts, external web apps, scheduled scripts, and any other programmatic interface that fetches fresh data on each run. Do NOT use it for agent-side analytics or one-off snapshot visualizations — use the `workspace_shell` tool with the connection query CLI instead. Pass the full workspace-relative `query_file` path including the connection prefix, e.g. `connections/<name>/queries/<file>`. Paths resolve from `/workspace`, not from any current directory. Author new query files through `workspace_shell` before calling this tool so query text is durable and reusable. Returns `rows` as a parsed list of record dicts and `row_count` as the total — no JSON parsing needed. Results are capped by `max_rows` (1–5000).
Install hosted demo data with no user credentials. Pass a demo id or natural-language request. Use `connection_setup` for real user-owned connections.
Run a shell command in the persistent /workspace runtime. Use for all agent-side work: query authoring, analytics, DuckDB joins, workspace files, scripts, git, diagnostics, and cron. The `connection` and `cron` CLIs exist only inside this runtime and must be invoked through this tool.
The MarcoPolo MCP integration connects your Dench AI CRM directly to MarcoPolo MCP, so agents can read and act on your MarcoPolo MCP data as part of everyday work — answering questions in chat, keeping your CRM in sync, and running automations without anyone copying data between tools.
5 actions are available for agents to invoke on your behalf. Every call runs through MarcoPolo MCP's own authorization, scoped to the account you connect.
Sign in to your Dench workspace and open Integrations.
Find MarcoPolo MCP and click Connect — you'll authorize access through MarcoPolo MCP's own sign-in flow. No API keys or code required.
Ask an agent to use MarcoPolo MCP in chat, or call it from an automation.
Manage or disconnect the connection any time from workspace settings.
The Dench MarcoPolo MCP integration connects your AI CRM to MarcoPolo MCP, so AI agents can work with your MarcoPolo MCP data as part of chats, automations, and CRM workflows. You connect your account once, and every agent in your workspace can use it — governed by your workspace permissions.
The MarcoPolo MCP integration currently exposes 5 actions, including Connection setup, Connections list, Data query, Install demo connection, and Workspace shell. Agents invoke them on your behalf from chat or from automations.
No. You connect MarcoPolo MCP from your Dench workspace using MarcoPolo MCP's own sign-in and authorization flow — no API keys to copy, no glue code to maintain.
Connections are authorized through MarcoPolo MCP's own authentication flow, and Dench stores only the authorization needed to act on your behalf. You can review and disconnect the MarcoPolo MCP connection from your workspace settings at any time.