Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 8 additions & 3 deletions skills/dataiku-headless-setup/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,13 @@ Bring a new or broken plugin installation to a verified Dataiku connection. A re
- Windows PowerShell: `powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"`
3. Obtain explicit approval, run only the selected installer, and verify with `uv --version`. Do not substitute a third-party package manager or edit shell startup files unless the user asks.
4. If the current agent process cannot see the newly installed executable, use the installer's reported location to confirm it exists, then ask the user to fully restart or reload the agent. Stop and resume setup in the new session; the already-running MCP process cannot repair its own launch environment.
5. Once uv is suitable, check whether the Dataiku MCP tools are available. If they are not, allow an initial dependency download to finish, then reload the plugin or restart the agent once before diagnosing a Dataiku connection problem.
6. When the MCP tools are available, run `list_instances`. If no instance is configured, run `configure_instance` and have the user complete the local setup page. If multiple instances exist without an active one, ask which to use and run `switch_instance`.
7. Verify the active profile with `get_current_instance`, then make a lightweight read-only Dataiku call such as `list_projects` to validate the saved connection. Never request or repeat the API key in chat.
5. Once uv is suitable, warm the runtime by running the server once with stdin closed. Locate the absolute path of this `SKILL.md`; the plugin root is its ancestor containing both `skills/` and `bin/` (this file is at `<plugin_root>/skills/dataiku-headless-setup/SKILL.md`). Do not assume the current working directory is the plugin root.
- macOS or Linux: `uv run --quiet --locked --script "<plugin_root>/bin/run_mcp.py" < /dev/null`
- Windows PowerShell: `$null | uv run --quiet --locked --script "<plugin_root>\bin\run_mcp.py"`

A startup line on stderr followed by exit status 0 is expected. Do not substitute `uv sync --locked --script`: it caches downloads but leaves environment creation for the first server launch.
6. Check whether the Dataiku MCP tools are available. If they are not, reload the plugin or restart the agent once before diagnosing a Dataiku connection problem.
7. When the MCP tools are available, run `list_instances`. If no instance is configured, run `configure_instance` and have the user complete the local setup page. If multiple instances exist without an active one, ask which to use and run `switch_instance`.
8. Verify the active profile with `get_current_instance`, then make a lightweight read-only Dataiku call such as `list_projects` to validate the saved connection. Never request or repeat the API key in chat.

Report completion with the uv version, active instance name and URL, Dataiku version when available, and whether the Dataiku read succeeded. If a restart is required, say that setup is incomplete and give the single next action.