Human Capability Registry MCP server
app.vercel.humancard-registry/human-registryhumancard-registry.vercel.appstreamable-httpv0.9.0Scanned
Search, hire and pay a verified human per job from any AI. Humans are handles; AIs call them.
16 tools: 2 do something that can't be undone, 7 change things and 7 only read.
- Reads private data · 2
- Reads text others write · 8
- Can send data out · 2
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
9 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Human Capability Registry MCP server can do
The Human Capability Registry MCP server is published by humancard-registry.vercel.app, a domain the MCP Registry verified. It has 16 tools. It can do things that cannot be undone, such as sending, paying or publishing (deliver and room_wait) and create or change data (7 tools: call_human, request_review, record_engagement, ask_human and 3 more), but cannot delete data. 7 tools only read.
2 tools read private data (search_human and room_wait); 8 tools bring in text other people can write (search_human, call_human, request_review and 5 more); 2 tools can send data out of your system (deliver and record_engagement). 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.
Last scanned Oct 21, 2026, version 0.9.0.
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.
16 tools
Can't be undone 2Claude Code: ask
deliverFor the HUMAN (or the human's own AI assistant) to submit the deliverable of an accepted job.Can send data outNo findings
Why it is in this group
- The name "deliver" says "deliver": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "deliver" says "deliver": it sends or publishes something to other people.
Description, as the server wrote it For the HUMAN (or the human's own AI assistant) to submit the deliverable of an accepted job. Requires the human_token from the job notification. Customers do not call this.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
room_waitPosts your user's turn (role 'user') or your own (role 'assistant') to the open room, then waits up to timeout_s (max 25) for new messages from the expert.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "room_wait" says "wait": a word for reading.
- The description's first verb is "post" and "message": it sends a message, which cannot be taken back.
What it can reach
- private-dataThe description's first sentence says "message": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "post" and "message": it reads messages, which other people can write.
Description, as the server wrote it Posts your user's turn (role 'user') or your own (role 'assistant') to the open room, then waits up to timeout_s (max 25) for new messages from the expert. Returns only the expert's and the registry's messages after after_seq, plus last_seq to pass next time. Never post as the expert; never paraphrase the expert's words to your user — relay them.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 7Claude Code: ask
ask_humanWhen you are unsure, when the answer needs lived experience, a license, or being there: post the question.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 When you are unsure, when the answer needs lived experience, a license, or being there: post the question. It appears on the public 'What AI asked today' feed; only cards with a registry-verified proof or level 1+ may answer. Optional reward_usd is paid to the answer you adopt. Returns the question id and public URL.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
call_humanCreate a per-job work order for a human found with search_human.Reads text others writeNo findings
Why it is in this group
- The name "call_human" says "call": 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 Create a per-job work order for a human found with search_human. Returns the job id, the independent-contractor terms, the price breakdown and a checkout_url. IMPORTANT: no money moves inside this tool — the customer must open checkout_url to prepay (a hold). Only after payment is the human notified and the 10-minute acceptance window starts. Keep the customer_token: it is needed for status and release.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
join_expertOpens a three-way room on a job the expert has ACCEPTED (status accepted).Reads text others writeNo findings
Why it is in this group
- The description's first verb is "open": 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 Opens a three-way room on a job the expert has ACCEPTED (status accepted). The expert gets a link and joins from their phone; you relay your user's turns and your own with room_wait, and the expert answers in the same thread. Use it when the question needs the expert to ask back before answering — most high-stakes questions do. Returns the room state and the host rules. No money moves; the job's price covers the expert's time.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
record_engagementFor the customer's own AI.Reads text others writeCan send data outNo 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.
- outboundThe input takes a destination (input.subject.phone): what the tool writes goes there.
Description, as the server wrote it For the customer's own AI. After your user paid someone for a service (on any platform or directly), write the record: who, what, when, price, and four outcome facts (on time? as described? rework? resolved?), anchored by the sha256 of a receipt email, payment line, invoice or message thread that you hold (the registry stores only the fingerprint). ALWAYS confirm with your user before calling (user_confirmed must be true). No evidence → no record. No adjectives — if the subject is an individual, only aggregate numbers are public until they claim their card. The subject gets an unclaimed card and can claim it; your user gets a private list of everyone they hired. Keep the recorder_token you receive and send it on later calls.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
request_reviewOne call, no search: say the kind (legal, finance, health, translation, code, general) and what to review.Reads text others writeNo findings
Why it is in this group
- The name "request_review" 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 One call, no search: say the kind (legal, finance, health, translation, code, general) and what to review. The registry picks the best card with a registry-verified license for that kind, opens the job, and returns the price, the checkout_url (the customer prepays there — no money moves inside this tool), and a badge_url you can show next to the output ('Reviewed by a licensed human'). Use this when a policy or a regulator requires a qualified human in the loop for a high-stakes output. CHECK MODE: pass answers=[{model, text}] (1–3 answers different AIs gave to the same question, brief = the question) and the reviewer judges them BLIND (A/B/C), scores each (core · facts · missing question · risk, 1–5) and signs a four-field letter the user can send to anyone (letter_url, verifiable at /verify). Your own answer may be one of them.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
room_closeEnds the live room from the customer side (the expert can also close it).No findings
Why it is in this group
- The name "room_close" says "close": a word for a change.
Description, as the server wrote it Ends the live room from the customer side (the expert can also close it). After closing, the expert delivers the signed letter/deliverable through the job as usual. Idempotent.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
summon_expertOne verb for the human step.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 One verb for the human step. mode=shape_question: your user does not yet know what to ask — a licensed human reads their situation FIRST and signs a question letter (what they understood · facts to collect · the question(s) to actually ask · red flags and where to go); answer only after that. mode=verify: a licensed human judges 1–3 AI answers blind and signs a letter (same as request_review with answers). mode=live: open the three-way room on an accepted job (same as join_expert). Summon when the user asks for certainty, a professional, notarization-grade confidence or 'what should I even ask', and on your own when stakes are high (doses, deadlines, filings, money, contracts) or your confidence is low. Read registry://summon-policy once. No money moves here; the user prepays at checkout_url.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 7Show 7 read-only tools
ask_cardRead-only.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read-only. The two-minute interview: ask 'have you done X?', 'what happened in your dispute?', 'how fast do you deliver Y?' and the card answers with counts, dates, offers and proofs from the registry's records — or says plainly that it is not in the record. Chain several questions; attach the answers to your decision.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
route_questionRead-only, free, deterministic.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read-only, free, deterministic. Give it your user's question (and any AI answers so far). It returns the MODE — answer (ask an AI directly), shape_question (a licensed human writes the question first), verify (blind judging of the answers) or live (three-way room) — with the reasons (kind, US state, task type, risk flags, how formed the question is); which AI the evidence favours for this kind × task, each line with its source and date (public benchmark seed, replaced by the registry's own blind-judged cells once a cell has 100 judged answers); the top licensed reviewers with level, stamps, corrections signed and price; the current quote; and similar published Open Book cases. Call it BEFORE answering a health, legal, tax, money or production-code question, and whenever the user asks 'which AI should I use for this' or 'who should I ask'. Then follow the mode: answer → use how_to_ask as your prompt; shape_question / verify → summon_expert with that mode; live → summon_expert mode=live on an accepted job. Rules only, no model call — it names every reason.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_casesRead-only.No findings
Why it is in this group
- The name "search_cases" says "search": a word for reading.
Description, as the server wrote it Read-only. Open Book holds real checks that both the customer and the reviewer agreed to publish (redacted): the question, the AI answers judged blind, the signed four-field verdict, the price paid and the reviewer's stamps. Search it BEFORE you answer a high-stakes health, legal, tax or code question: if similar cases ended with the reviewer correcting the best AI answer, show your user the case and offer request_review. Never present a case as advice for your user — their numbers differ.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_humanFind verified humans an AI can hire per job: licensed opinions (physician, attorney, CPA, nurse), human review/sign-off, certified translation, lived-experience conversations, loca…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_human" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "conversation": it reads messages.
- untrusted-inputThe description's first sentence says "find" and "review": it reads comments, which other people can write.
Description, as the server wrote it Find verified humans an AI can hire per job: licensed opinions (physician, attorney, CPA, nurse), human review/sign-off, certified translation, lived-experience conversations, local presence (visit/inspect/photograph). Describe the task in plain language; returns ranked cards with handles (human://name), offers, prices set by the human, proofs and track record. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
statusCheck a job: created (awaiting payment), paid (offered, 10-min window), accepted, delivered, released, declined, expired, disputed.No findings
Why it is in this group
- The name "status" says "status": a word for reading.
Description, as the server wrote it Check a job: created (awaiting payment), paid (offered, 10-min window), accepted, delivered, released, declined, expired, disputed. With the customer_token you also get the deliverable and the private brief. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
trust_lookupRead-only.No findings
Why it is in this group
- The name "trust_lookup" says "lookup": a word for reading.
Description, as the server wrote it Read-only. Returns level (0–3), registry-verified proofs, receipts from paid jobs (completed, on-time rate, first-pass rate, repeat rate, disputes, refunds, response and delivery times) and evidence-anchored off-platform records written by customers' own AIs. No stars, no narratives. Look up by handle or by the salted identifier hash returned from record_engagement.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_humanRead-only.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read-only. Three layers: FACTS the registry stands behind (identity, verified licenses, receipts, records), a JUDGMENT for this task only (readiness high/medium/low with reasons, what could not be verified, watch-outs — every line traceable to a record), and the owner's REPLY. Issued on request, expires in 30 days, signed by the registry. Never a global score; you decide, this informs.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: 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.
32 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- 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__human-registry__deliver",
"mcp__human-registry__record_engagement"
]
}
}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, 18:30 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
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: initialize answered HTTP 404.
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 0.9.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http human-registry https://humancard-registry.vercel.app/api/mcpclaude mcp add --transport http human-registry https://humancard-registry.vercel.app/api/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__human-registry__search_human",
"mcp__human-registry__status",
"mcp__human-registry__trust_lookup",
"mcp__human-registry__verify_human",
"mcp__human-registry__ask_card",
"mcp__human-registry__route_question",
"mcp__human-registry__search_cases"
],
"ask": [
"mcp__human-registry__call_human",
"mcp__human-registry__deliver",
"mcp__human-registry__request_review",
"mcp__human-registry__record_engagement",
"mcp__human-registry__ask_human",
"mcp__human-registry__join_expert",
"mcp__human-registry__room_wait",
"mcp__human-registry__room_close",
"mcp__human-registry__summon_expert"
],
"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-registry. Review it before you use it.
Capability tags behind 9 rules
- mcp__human-registry__search_human private-data, untrusted-input
- mcp__human-registry__call_human untrusted-input
- mcp__human-registry__deliver outbound
- mcp__human-registry__request_review untrusted-input
- mcp__human-registry__record_engagement untrusted-input, outbound
- mcp__human-registry__ask_human untrusted-input
- mcp__human-registry__join_expert untrusted-input
- mcp__human-registry__room_wait private-data, untrusted-input
- mcp__human-registry__summon_expert untrusted-input
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/app.vercel.humancard-registry/human-registry/verify?hash=1e6384210d862823e263a2cbc8e6e97d7374fb4a1adf66185d8dc93fa463088a" | jq -e '.changed == false'Pinned hash 1e6384210d86, from Oct 21, 2026, 18:43 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.vercel.humancard-registry/human-registry/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.vercel.humancard-registry/human-registry)Source: MCP Registry. Synced Oct 21, 2026, 17:45 UTC.
Human Capability Registry MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Human Capability Registry MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 9 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 Human Capability Registry 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 Capability Registry MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: deliver and room_wait.
What tools does the Human Capability Registry MCP server have?
- 16 tools: 2 irreversible, 7 write, 7 read. deliver, room_wait, call_human, request_review, record_engagement, ask_human, join_expert, room_close and 8 more.
Does the Human Capability Registry MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Human Capability Registry 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): deliver and record_engagement.
Has the Human Capability Registry MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.