MCP server for HumanRail — route tasks requiring human judgment to vetted workers from any AI agent
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport stdio counts 7 tools · 0 res
· 0 prompts
permission surface via README inference
tools
-
cancel_task
Cancel a pending task
-
create_task
Route a task to a human worker for review/judgment
-
get_task
Check the status and result of a task
-
get_usage
View usage stats and billing summary
-
health_check
Check if the HumanRail API is reachable
-
list_tasks
List tasks with filters (status, type, date range)
-
wait_for_task
Poll until a task completes (blocking)
evidence-backed
findings quoted directly from the published source artifact — not inferred
This server hasn't been statically analyzed yet (npm/PyPI artifacts only).