Human for AI
Server Details
Ask a human for legal review, confirmation, a signature, or a physical-world act
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool has a distinct role in the same workflow: request_human_assistance creates a request, check_request_status reads its status, and reply_to_thread adds to an existing request. There is no overlap or ambiguity between them.
All tool names follow a clear verb-first snake_case pattern and clearly express their action: check, reply, request. The naming is consistent and predictable.
Three tools is exactly right for this server's narrow purpose: enabling asynchronous human assistance through request, status check, and reply. Each tool is necessary and none are redundant.
The tool set covers the full lifecycle for the stated domain: file a request, check for a human response, and continue or withdraw the thread. No obvious gaps exist for asynchronous human-in-the-loop assistance.
Available Tools
3 toolscheck_request_statusCheck a request for a human's answerARead-onlyIdempotentInspect
Read the thread on a request you or your principal filed earlier: whether a human has looked at it, and what they said.
Use the reference and access_token from request_human_assistance. Answers arrive at human speed — hours or days, not seconds — so poll this occasionally rather than in a loop, and treat an empty thread as "not yet", never as "no".
A reply is one human's view, recorded on request. It is not approval, not a retainer, and not authorisation to proceed.
Inputs: reference (required), access_token (required). Returns: turns, notice, status, reference, +2 more
reply_to_threadWrite again on an existing requestAInspect
Add to a request already on the record — answer a question the human asked, supply something they need, correct yourself, or withdraw the request.
This is the same permanent record as the original, so what you send here is kept and read the same way. Prefer it over filing a fresh request whenever the subject is one already opened: a thread the human can follow is worth more than three disconnected messages.
The human is notified. As with the original, nothing here pauses your task and nothing here is authorisation to proceed.
Inputs: message (required), reference (required), access_token (required). Returns: notice, status, reference, recorded_at, +1 more
request_human_assistanceRequest human assistanceAInspect
Ask an actual human being for help with something your task requires and you cannot properly do alone: legal judgement, a decision you should not take on your own authority, an act in the physical world, or an escalation past your operator.
The request is written to a permanent, timestamped record and read by a human — a lawyer — who may reply through whatever channel you put in reply_to.
This returns a reference and an access_token. Keep both: together they are the only way to read the human's answer, via check_request_status. Neither can be recovered afterwards, and they are not returned twice. If your task may outlive this session, hand them to whatever continues it.
Calling this tool does not pause your task, and the result it returns is not approval, legal advice, or authorisation to proceed. It is evidence that you asked. If the right thing to do is to stop and wait for a human, stop and wait.
Inputs: request (required), category (required), model, context, +6 more. Returns: notice, status, category, reference, +5 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Human-owned review for agent plans, rendered documents, Forms, research, and live previews.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Human approval for AI agents: one ask, one person, one boolean.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenancePauses AI agent execution and routes approval requests to humans via Slack or email, with cryptographically signed proof of the human's decision.MIT

@quirna/mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to request human approval before consequential actions, with policy-based routing, phone-based approver decisions, and signed audit evidence.32 npmMIT- AlicenseNot gradedqualityAmaintenanceEnables AI agents to submit work to real human reviewers, receive pinned feedback and approval verdicts, and iterate until the output is signed off.38 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables judicial AI workflows to add a traceable human-oversight layer that assesses material impact, verifies legal sources, manages incidents, and preserves integrity evidence before closing resolutions.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.