MarcoPolo

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`.

connection_setup

List visible Marcopolo connections ready in the execution workspace. Use connection.name with the connection CLI through workspace_shell. Entries with connection.queryable=false need provider authorization; follow their connection.next_step and note. Each entry lists its capabilities; only run queries against a connection whose capabilities include 'query'.

connections_list

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-driven queries 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).

data_query

Install hosted demo data with no user credentials. Pass a demo id or natural-language request. Use `connection_setup` for real user-owned connections.

install_demo_connection

Run a shell command in the persistent /workspace runtime. Use for all agent-side work: query authoring, data analysis, DuckDB joins, workspace files, scripts, git, diagnostics, and scheduling. The `connection` CLI exists only inside this runtime and must be invoked through this tool. Commands that outlive `timeout` keep running for up to 300 seconds and return an `execution_id`; check them with `execution status <execution_id>` through this tool. Use `execution list` to see running and recent workspace executions and `execution cancel <id>` to stop one. By default, clients on an account share four foreground slots per API process and two background slots per workspace. Standalone execution management commands remain available when work slots are full and do not create execution records. Cancellation stops the supervised shell process group; detached processes and queries already dispatched to the connection daemon may continue.

workspace_shell