Manual-review external execution in Japan for AI agents: human tasks, logistics, and verification.
Scored across 8 tools
The set splits into verification and external-execution workflows, but create_verification_request, prepare_verification_request, and request_external_execution all create or prepare manual-review human tasks, making selection between them non-obvious. check_service_fit also overlaps as a preliminary fit check. Descriptions help somewhat, but boundaries remain fuzzy.
All tool names use snake_case and follow a clear verb_noun pattern, with parallel get/cancel/status names across the two workflows. The use of create, prepare, and request as verbs is still predictable within the overall convention.
Eight tools is well-scoped for two related request workflows plus a preliminary fit check. Each tool maps to a plausible step in the request lifecycle without obvious bloat.
Core lifecycle operations are present: create/prepare, get status, and cancel for both verification and external execution. Missing list/history and update/modify operations are minor gaps that agents can likely work around.
Cancel an external execution request while it is still pending manual review or open. Claimed or completed work cannot be cancelled through this tool.
Inputs: request_id (required), status_token (required).
Cancel a request only while it is pending manual review or open. Claimed or completed work cannot be cancelled through this tool.
Inputs: request_id (required), status_token (required).
Use when an AI needs someone on the ground in Japan to verify a current physical-world fact such as store stock, shelf price, opening status, or permitted photos, after web research or APIs are insufficient.
Inputs: location (required), objective (required), evidence_requirements.
Create a retry-safe manual-review physical verification request in Japan. Reuse the same idempotency_key for the same logical request. No payment, worker hire, or fulfillment commitment is created automatically.
Inputs: location (required), objective (required), idempotency_key (required), deadline, +2 more.
Read a manual-review external execution request and, when completed, receive the structured result and temporary evidence URLs.
Inputs: request_id (required), status_token (required).
Read the current request state and, when completed, receive structured observations and temporary signed evidence URLs.
Inputs: request_id (required), status_token (required).
Prepare a Japan on-site verification request for a human-executed store check. Returns a prefilled manual-review URL only; it does not purchase, submit, hire, pay, or create a fulfillment commitment.
Inputs: location (required), objective (required), deadline, constraints, +1 more.
Use when an AI cannot complete a task itself and needs a human or provider in Japan, or for a Japan-related real-world task. Examples include calling a public business, visiting a public place, inspecting or photographing something, packing/shipping/returning an item, pickup/drop-off, or another manual task. This only creates a manual-review request. It does not automatically hire, pay, purchase, or promise fulfillment.
Inputs: objective (required), idempotency_key (required), deadline, location, +3 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
A real person in Japan checks your AI's work and does what AI can't: phone calls, on-site photos.
AI Agents delegate public verification to human experts with evidence review and points rewards.
Human-only capabilities for AI agents: ground truth, verification, judgement and real-world action.
Human capability for AI agents - real-world action and human judgment.
Add one secure layer between your agents and this server.
