Hand bounded tasks from AI agents to trusted humans.
Scored across 4 tools
Each tool has a clearly distinct purpose: fee quote creation, task creation, compliance review retrieval, and task retrieval. The workflow ordering and resource/action boundaries are explicit enough that an agent should not confuse them.
All tools follow the same predictable humanleg_ + verb_noun pattern: create_fee_quote, create_task, get_compliance_review, get_task. There are no mixed conventions or vague names.
Four tools is a well-scoped set for a narrow task-creation and compliance-review workflow. Each tool earns its place and there is no obvious filler.
The surface covers creating a task, retrieving it, and retrieving its compliance review, but it lacks lifecycle operations such as updating, canceling, listing, funding, or publishing tasks. Since create_task explicitly does not fund or publish, agents hit a dead end for completing the full task lifecycle.
Create a short-lived synthetic fee quote before creating a task.
Inputs: displayAud (required), rewardUsdc (required).
Create a bounded task and run compliance review. This does not fund or publish the task.
Inputs: title (required), deadline (required), displayAud (required), feeQuoteId (required), +3 more.
Retrieve the exact-content compliance decision for a task.
Inputs: taskId (required).
Retrieve the current task, content version, hash and lifecycle status.
Inputs: taskId (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
API for AI agents to delegate tasks to real humans.
Human-as-a-Service for AI agents. Delegate tasks that need a real human, get results via API.
Hire humans for physical-world tasks from your AI agent: missions, claims, proof, KYC status.
Human execution API for AI agents needing voluntary help with physical-world tasks.
Add one secure layer between your agents and this server.
