Liveness check - always succeeds if the MCP server is running.

Use this to verify the Bernstein MCP connection is still alive.

Returns: JSON with status "ok".

Start an orchestration run by posting a task to the Bernstein server.

Args: goal: Description of what you want Bernstein to accomplish. role: Specialist role to assign (backend, frontend, qa, security, …). priority: 1=critical, 2=normal, 3=nice-to-have. scope: Task scope - small, medium, or large. complexity: Task complexity - low, medium, or high. estimated_minutes: Rough time estimate in minutes.

Returns: JSON with the created task ID, title, and status.

Return a summary of all task counts from the Bernstein server.

Returns: JSON with total, open, claimed, done, failed counts plus a per-role breakdown.

List tasks from the Bernstein server.

Args: status: Optional filter - open, claimed, in_progress, done, failed, blocked, or cancelled.

Returns: JSON array of task objects.

Return cost summary (total USD spent and per-role breakdown).

Returns: JSON with total_cost_usd and per-role cost breakdown.

Request a graceful Bernstein shutdown by writing a SHUTDOWN signal.

Writes .sdd/runtime/signals/SHUTDOWN in the project directory, which the orchestrator detects and shuts down gracefully.

Args: workdir: Project root directory (default: current directory).

Returns: Confirmation message.

Approve a pending or blocked task, marking it complete.

This is used for approval gates - when a task is awaiting human sign-off before proceeding.

Args: task_id: ID of the task to approve. note: Optional approval note recorded as the result summary.

Returns: JSON with the updated task status.

Create a subtask linked to a parent task.

Agents call this to decompose their current work into subtasks during execution. The parent task is automatically transitioned to WAITING_FOR_SUBTASKS status.

Args: parent_task_id: ID of the parent task that this subtask belongs to. goal: Description of what the subtask should accomplish. role: Specialist role to assign (backend, frontend, qa, …). priority: 1=critical, 2=normal, 3=nice-to-have. scope: Task scope - small, medium, or large. complexity: Task complexity - low, medium, or high. estimated_minutes: Rough time estimate in minutes.

Returns: JSON with the created subtask ID, parent_task_id, title, and status.

Load a skill pack body (and optionally a reference or script).

Agents receive only a compact skill index in their system prompt. Call this tool to fetch the full SKILL.md body for a skill when you decide it's relevant to the current task. Pass reference to get a deeper-context file or script to read the content of an executable helper.

Args: name: Skill name (matches the index entry, e.g. "backend"). reference: Optional filename under references/ - for example "python-conventions.md". script: Optional filename under scripts/ - for example "lint.sh". The script content is returned as text; the MCP harness does not execute it.

Returns: JSON with name, body, available_references, available_scripts, and the optional fetched content.