Human for AI
REMOTE · YOURHUMAN.AI
Ask a human for legal review, confirmation, a signature, or a physical-world act
Available components
Last scanned (13 hours ago)
Scores higher than 92% of remote servers
Reachable. Last reached 7 Nov 2026.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1223 tokens (~407/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 13 Sept 26 0
- Stability: 0.97 → pass security
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 22 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “request_human_assistance” rewrote its description, which is the text the model reads security
- Schema quality: 703 → 407 ▲ functional
- New tool “check_request_status” functional
- New tool “reply_to_thread” functional
- 17 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- 15 Aug 26 0
- Stability: unverified → 0.03 ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 7 Nov 2026 · Probed https://yourhuman.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=yourhuman.ai | CN=WR3,O=Google Trust Services,C=US | 5 Oct 2026 | 3 Jan 2027 | RSA 2048 | SHA256-RSA | b978d90f68cb3adb0abf3053aeca25fb |
| SANs: yourhuman.ai | ||||||
| CN=WR3,O=Google Trust Services,C=US (CA) | CN=GTS Root R1,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | RSA 2048 | SHA256-RSA | 7ff005a91568d63abc22861684aa4b5a |
| CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 19 Jun 2020 | 28 Jan 2028 | RSA 4096 | SHA256-RSA | 77bd0d6cdb36f91aea210fc4f058d30d |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of yourhuman.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814, 3799 | 8, 8 | Verified |
| yourhuman.ai. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=2592000; includeSubDomains |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | same-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://yourhuman.ai/mcp | Verified | 200 | |
| http (plaintext) | http://yourhuman.ai/mcp | HTTPS enforced | 302 | https://yourhuman.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_request_status Check a request for a human's answer ~178
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.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | yes | The access_token returned alongside that reference. Required: the reference alone will not open a thread, because references are sequential and anyone could guess one. |
| reference | string | yes | The reference you were given, e.g. 'HFA-00042'. |
| Name | Type | Req | Description |
|---|---|---|---|
| human_has_replied | boolean | yes | – |
| notice | string | yes | – |
| received_at | string | yes | – |
| reference | string | yes | – |
| status | string | yes | `recorded` — filed, nobody has read it yet; `reviewed` — a human has read it but not answered; `answered` — there is a reply below; `declined` — the human will not take it on; `closed` — ended withou… |
| turns | array | yes | The whole thread, oldest first. |
No examples provided.
reply_to_thread Write again on an existing request ~198
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.
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | yes | The access_token returned alongside that reference. Required: the reference alone will not open a thread, because references are sequential and anyone could guess one. |
| message | string | yes | What you want to add. Self-contained: the reader has the thread but not your context window. |
| reference | string | yes | The reference you were given, e.g. 'HFA-00042'. |
| Name | Type | Req | Description |
|---|---|---|---|
| notice | string | yes | – |
| recorded_at | string | yes | – |
| reference | string | yes | – |
| status | string | yes | – |
| thread_status | string | yes | – |
No examples provided.
request_human_assistance Request human assistance ~669
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | What you call yourself. |
| category | string | yes | Which kind of human intervention you need. `legal_review`: a human lawyer should read this before you act — contracts, terms, licences, liability, regulatory exposure, or anything where being wrong h… |
| context | string | – | Background the human needs to answer: the task you are carrying out, who it is for, what you have already done, and the relevant facts or documents. |
| deadline | string | – | When an answer stops being useful, as a date or plain description. Optional. |
| model | string | – | Your underlying model, e.g. 'claude-opus-5'. |
| operator | string | – | Who runs you, or on whose behalf you are acting. Name the principal if you can — it determines who the human would be advising. |
| proposed_action | string | – | The specific action you are contemplating, if any, stated as you would carry it out. Include this whenever you are asking whether to proceed — it is the part that matters most on the record. |
| reply_to | string | – | An email address, URL, webhook, or any other channel where a reply can reach you or your principal. Without this the human can record your request but cannot answer it. |
| request | string | yes | What you are asking the human to do. Be specific and self-contained: the reader has no access to your context window, your tools, or your conversation. |
| urgency | string | – | `routine` — no deadline; `soon` — a human answer is needed within days; `blocking` — you have halted your task and cannot continue without a human. |
| Name | Type | Req | Description |
|---|---|---|---|
| access_token | string | yes | Secret. Pass with the reference to `check_request_status` to read the answer. Not recoverable and not shown again. |
| category | string | yes | – |
| human_has_reviewed | boolean | yes | Always false at this point. A human reads the record afterwards, at human speed. |
| notice | string | yes | – |
| received_at | string | yes | – |
| reference | string | yes | Quote this in any later correspondence. |
| reply_expected_via | string|null | yes | The channel you supplied, or null if you gave none. |
| status | string | yes | – |
| thread_url | string | yes | The same thread over plain HTTP, for anything that can fetch a URL but not call this server. GET it for JSON. |
No examples provided.
How do I install the Human for AI MCP server?
Human for AI is a hosted endpoint at https://yourhuman.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · yourhuman.ai
claude mcp add --transport http ai-yourhuman-human-for-ai 'https://yourhuman.ai/mcp'
What is the Human for AI MCP server?
Human for AI is an MCP server listed in the public MCP registry as ai.yourhuman/human-for-ai. Ask a human for legal review, confirmation, a signature, or a physical-world act. This page covers its hosted endpoint (https://yourhuman.ai/mcp).
Is the Human for AI MCP server safe to use?
Human for AI scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Human for AI MCP server expose?
Human for AI exposes 3 tools: request_human_assistance, check_request_status, reply_to_thread. Their descriptions and schemas cost roughly 1,045 tokens of context every time the server is loaded.
Does the Human for AI MCP server require authentication?
No. We connected to Human for AI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Human for AI MCP server still maintained?
Human for AI is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Human for AI MCP server?
VerifyMCP ran 13 checks on Human for AI, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.