Anter MCP Server

Running & observability

These tools close the loop between designing an agent and seeing it work: run_agent triggers a real execution, and the remaining tools let you inspect what happened — the same data behind the Executions view in Flows.

Running an agent

run_agent{ agentId | agentSlug, message, target? }

Triggers a real, billable run of an agent — the same execution path the chat interface, playground, and external API all use. Resolve the agent by either agentId or agentSlug.

  • target defaults to draft — deliberately different from other run surfaces, so testing an agent you're actively revising with update_agent_spec doesn't accidentally re-run the old live version. Pass target: "live" explicitly to run the promoted version instead.
  • The tool call returns as soon as it can meaningfully report a result: a completed answer, an awaiting_approval status if the agent paused on a permission check, or a running status with an execution id if the agent is still working past the tool's wait budget. A running result is never aborted — poll get_workflow_execution or get_session_history with the returned id to get the eventual outcome.
  • Only one run_agent call runs per agent at a time — a second call for the same agent while one is in flight returns an already_running status instead of piling up concurrent runs.

This is a real run

run_agent consumes LLM tokens and executes any tools the agent has attached, subject to its permission mode, exactly like a run started from the chat interface. It is not a dry run or simulation.

Reading back results

ToolWhat it returns
get_workflow_executionStatus, timing, and metadata for one execution, by execution id
get_session_historyThe full conversation history for a session — every message exchanged
list_agent_conversationsA summary per conversation for a given agent — one row per distinct conversation
list_conversation_executionsEvery execution that belongs to one specific conversation

Understanding what you see

get_runtime_semantics_guide{ topics?: [...] }

A reference for interpreting execution data: the ReAct execution model, transfer vs. delegation between sub-agents, the routing-event glossary, permission modes, and how memory persists across a session. Call it with no arguments for a compact index of topics, or pass specific topic keys for the full detail on just those.

Reading a multi-agent trace

If a run routes across several sub-agents and the trace isn't self-explanatory, call get_runtime_semantics_guide with the routing_events_reference topic — it's a glossary for every event type you'll see in get_workflow_execution's routing timeline.