PromptHuman MCP server
io.github.prompthumanhq/prompthumanprompthumanhqstreamable-httpv0.1.0Scanned
Paid human judgment for AI agents: gut checks, how text reads, plausibility, local context.
6 tools: 3 do something that can't be undone, 1 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here do something that can't be undone. Govern them.
- 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 PromptHuman MCP server can do
The PromptHuman MCP server is published by the GitHub account prompthumanhq. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_followup, request_refund and send_feedback) and create or change data (1 tool: ask_human), but cannot delete data. 2 tools only read.
1 tool reads private data (check_status); 4 tools bring in text other people can write (ask_human, check_status, send_followup and 1 more); 2 tools can send data out of your system (send_followup and send_feedback). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 19, 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.
6 tools
Can't be undone 3Claude Code: ask
request_refundAsk for a refund on a paid PromptHuman conversation, for example because a reply deadline was missed.Reads text others writeNo findings
Why it is in this group
- The name "request_refund" says "request": a word for a change.
- The name "request_refund" also says "refund": a word that usually means money moves, which cannot be taken back.
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 for a refund on a paid PromptHuman conversation, for example because a reply deadline was missed. Explain why in reason.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
send_feedbackTell us whether a PromptHuman answer helped and whether it changed what you did next.Can send data outNo findings
Why it is in this group
- The name "send_feedback" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "send_feedback" says "send": it sends or publishes something to other people.
Description, as the server wrote it Tell us whether a PromptHuman answer helped and whether it changed what you did next. Takes seconds and helps us improve.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
send_followupSend a follow-up message in a PromptHuman conversation after a human has replied.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_followup" says "send": 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 "send_followup" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send a follow-up message in a PromptHuman conversation after a human has replied. Only works when check_status shows can_send_followup: true. Max 300 words; no sensitive data.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 1Claude Code: ask
ask_humanAsk a real person for human judgment when you need it: a gut check, how something will read to a person, whether a plan is plausible, local or cultural context, or a tie-breaking c…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
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 a real person for human judgment when you need it: a gut check, how something will read to a person, whether a plan is plausible, local or cultural context, or a tie-breaking call. Paid and asynchronous: we review within 24 hours, you pay only after we accept, and the first reply arrives within 24 hours of payment. Never include passwords, keys, card or ID numbers, health records, or other people's personal data. Returns a conversation_id and access_token to use with check_status.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
check_statusGet the status of a PromptHuman request: whether it was accepted, the payment link, reply deadlines, the full message thread, and how many words and replies remain.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "check_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "reply": it reads comments, which other people can write.
Description, as the server wrote it Get the status of a PromptHuman request: whether it was accepted, the payment link, reply deadlines, the full message thread, and how many words and replies remain. Poll at most once every 10 minutes.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_prompthuman_infoGet PromptHuman's tiers, prices, word limits, turnaround times, refund rules, out-of-scope list and sensitive-data rules.No findings
Why it is in this group
- The name "get_prompthuman_info" says "get": a word for reading.
Description, as the server wrote it Get PromptHuman's tiers, prices, word limits, turnaround times, refund rules, out-of-scope list and sensitive-data rules. Call this before your first ask_human.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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.
8 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__prompthuman__check_status"
]
}
}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, 18:20 UTC, unchanged since Nov 20, 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
- 4
- 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 4 tools that change things (3 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://prompthuman-api.prompthumanhq.workers.dev/mcp: tools/list returned 6 tools to an anonymous client, including send_followup (irreversible), request_refund (irreversible), send_feedback (irreversible), ask_human (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 prompthuman https://prompthuman-api.prompthumanhq.workers.dev/mcpclaude mcp add --transport http prompthuman https://prompthuman-api.prompthumanhq.workers.dev/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": [
"mcp__prompthuman__get_prompthuman_info",
"mcp__prompthuman__check_status"
],
"ask": [
"mcp__prompthuman__ask_human",
"mcp__prompthuman__send_followup",
"mcp__prompthuman__request_refund",
"mcp__prompthuman__send_feedback"
],
"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 prompthuman. Review it before you use it.
Capability tags behind 5 rules
- mcp__prompthuman__ask_human untrusted-input
- mcp__prompthuman__check_status private-data, untrusted-input
- mcp__prompthuman__send_followup untrusted-input, outbound
- mcp__prompthuman__request_refund untrusted-input
- mcp__prompthuman__send_feedback 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/io.github.prompthumanhq/prompthuman/verify?hash=ab8fbfe281553717cfbf3f53a3609818634c27252b949ea738575038e80b7b0b" | jq -e '.changed == false'Pinned hash ab8fbfe28155, from Nov 19, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.prompthumanhq/prompthuman/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.prompthumanhq/prompthuman)Source: MCP Registry. Synced Nov 19, 2026, 21:18 UTC.
PromptHuman MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PromptHuman MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the PromptHuman MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PromptHuman MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: send_followup, request_refund and send_feedback.
What tools does the PromptHuman MCP server have?
- 6 tools: 3 irreversible, 1 write, 2 read. send_followup, request_refund, send_feedback, ask_human, get_prompthuman_info and check_status.
Does the PromptHuman MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PromptHuman MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_followup and send_feedback.
Has the PromptHuman MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.