Human for AI MCP server
ai.yourhuman/human-for-aiyourhuman.aistreamable-httpv0.1.0Scanned
Ask a human for legal review, confirmation, a signature, or a physical-world act
3 tools: 1 do something that can't be undone and 2 change things.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Human for AI MCP server can do
The Human for AI MCP server is published by yourhuman.ai, a domain the MCP Registry verified. It has 3 tools. It can do things that cannot be undone, such as sending, paying or publishing (reply_to_thread) and create or change data (2 tools: request_human_assistance and check_request_status), but cannot delete data. None of its tools only reads.
3 tools bring in text other people can write (request_human_assistance, check_request_status and reply_to_thread); 1 tool can send data out of your system (reply_to_thread).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Can't be undone 1Claude Code: ask
reply_to_threadAdd to a request already on the record — answer a question the human asked, supply something they need, correct yourself, or withdraw the request.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "reply_to_thread" says "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "reply_to_thread" says "reply": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- title: Write again on an existing request
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 2Claude Code: ask
check_request_statusRead the thread on a request you or your principal filed earlier: whether a human has looked at it, and what they said.Reads text others write1 finding
Why it is in this group
- The name "check_request_status" says "request": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "check_request_status" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_request_status" says "request": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Check a request for a human's answer
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
request_human_assistanceAsk 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…Reads text others writeNo findings
Why it is in this group
- The name "request_human_assistance" says "request": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Request human assistance
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:28 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://yourhuman.ai/mcp: tools/list returned 3 tools to an anonymous client, including reply_to_thread (irreversible), request_human_assistance (write), check_request_status (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "check_request_status" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_request_status" says "request": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http human-for-ai https://yourhuman.ai/mcpclaude mcp add --transport http human-for-ai https://yourhuman.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__human-for-ai__request_human_assistance",
"mcp__human-for-ai__check_request_status",
"mcp__human-for-ai__reply_to_thread"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as human-for-ai. Review it before you use it.
Capability tags behind 3 rules
- mcp__human-for-ai__request_human_assistance untrusted-input
- mcp__human-for-ai__check_request_status untrusted-input
- mcp__human-for-ai__reply_to_thread untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.yourhuman/human-for-ai/verify?hash=1ea7ac83d6468bd187053a1213efc30809e1ecba3d0b3a18952bf0fe58f5c721" | jq -e '.changed == false'Pinned hash 1ea7ac83d646, from Nov 11, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.yourhuman/human-for-ai/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.yourhuman/human-for-ai)Source: MCP Registry. Synced Oct 21, 2026, 17:44 UTC.
Human for AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Human for AI MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Human for AI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Human for AI MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: reply_to_thread.
What tools does the Human for AI MCP server have?
- 3 tools: 1 irreversible, 2 write. reply_to_thread, request_human_assistance and check_request_status.
Does the Human for AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Human for AI MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): reply_to_thread.
Has the Human for AI MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.