List all projects in the authenticated organization.

Use this to discover which projects exist before listing or creating agents. Returns each project's id, name, and slug.

List agents in the organization, optionally filtered by project.

Pass project_id (UUID from list_projects) to scope the results to a single project. Each agent record includes its tools and configuration.

Get full details of a single agent including its tools and system prompt.

Args: agent_id: The agent's UUID (from list_agents or create_agent).

Create a new agent.

Pass description to let the server auto-generate a detailed system prompt (scaffold_applied: true in the response). Pass prompt to set the system prompt directly. At least one of description or prompt is recommended.

Args: name: Display name for the agent. project_id: UUID of the project this agent belongs to (from list_projects). description: Natural-language description — triggers server-side prompt scaffolding. prompt: Raw system prompt to use as-is (skips scaffolding). framework: Execution framework. Defaults to langchain. tools: List of tool UUIDs to attach (from list_tools).

Update an agent's name, prompt, or tools.

Providing description re-runs server-side prompt scaffolding and overwrites the current system prompt. Providing prompt sets it directly. Providing tools replaces the full tool list.

Args: agent_id: The agent's UUID. name: New display name. description: New description — triggers re-scaffolding. prompt: New raw system prompt. tools: Replacement list of tool UUIDs.

PERMANENTLY delete an agent and all its logs, memories, and threads.

This action is irreversible. Double-check the agent_id before calling.

Args: agent_id: The agent's UUID.

Start an asynchronous agent run and return immediately.

Returns an execution_id — use get_run_status to poll for completion or get_run_logs to fetch the full output once done.

Args: agent_id: The agent's UUID. prompt: The user message / task for the agent to execute. thread_id: Conversation thread UUID for memory continuity across runs. params: Optional extra parameters passed to the agent.

Poll the status of a specific run.

Status values: queued → running → completed | error | cancelled | paused (waiting for approval).

Poll every 3-5 seconds. Most agents complete within 30-60 seconds.

Args: agent_id: The agent's UUID. execution_id: The execution UUID returned by run_agent.

Fetch the full event log for a completed run in chronological order.

Returns every event (start, tool_call, memory_access, completion, error, …) so you can see exactly what the agent did and what it returned.

Args: agent_id: The agent's UUID. execution_id: The execution UUID returned by run_agent.

List recent runs for an agent with their status and duration.

Useful for reviewing run history or checking whether a previous run succeeded before starting a new one.

Args: agent_id: The agent's UUID. limit: Number of runs to return (default 10, max 50).

List orchestrations in the organization, optionally filtered by project.

Pass project_id (UUID from list_projects) to scope results to a single project. Each orchestration includes its members and their attached tools.

Get full details of a single orchestration including its members and tools.

Args: orchestration_id: The orchestration's UUID (from list_orchestrations).

Start an asynchronous orchestration run and return immediately.

Returns an execution_id — use test_orchestration to block until completion or poll /executions for status updates.

Args: orchestration_id: The orchestration's UUID. input_data: Input data passed to the orchestration (e.g. {"query": "…"}). params: Optional extra execution parameters.

Quick synchronous test of an agent with a 90-second timeout.

Starts a run and polls every 2 seconds until it completes (or times out). Reports progress via MCP notifications while waiting. Returns the final status and execution_id. Use get_run_logs afterwards to see the output.

For production usage, prefer run_agent + get_run_status (non-blocking).

Args: agent_id: The agent's UUID. prompt: The test prompt to send.

Quick synchronous test of an orchestration with a 90-second timeout.

Starts a run and polls every 2 seconds until it completes (or times out). Reports progress via MCP notifications while waiting. Returns the final status and execution_id.

Args: orchestration_id: The orchestration's UUID. input_data: Optional input data for the orchestration run.

List all tools available to attach to agents.

Returns both built-in tools (shared across all orgs) and custom tools belonging to your organization. Use the uuid field when creating or updating agents with the tools parameter.