app.vercel.humancard-registry/human-registry

Est-ce que app.vercel.humancard-registry/human-registry est sûr ?

Au dernier audit MCP Hub, le serveur MCP « app.vercel.humancard-registry/human-registry » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 16 outils

• ask_card≈ 206 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • handle · string · requis
  • question · string · requis

  Exemple d'appel

  {"name": "ask_card", "arguments": {"handle": "texte", "question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ask_human≈ 272 tokens

  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.

  Paramètres, retour & exemple (6)

  Paramètres

  • context · string · optionnel
    What you tried, what is at stake (no personal data)
  • agent_id · string · optionnel
  • ai_model · string · optionnel
  • question · string · requis
  • ai_vendor · string · optionnel
  • reward_usd · number · optionnel

  Exemple d'appel

  {"name": "ask_human", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• call_human≈ 590 tokens

  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.

  Paramètres, retour & exemple (11)

  Paramètres

  • brief · string · requis
    What exactly you need. Private between customer and human; never shown on the public ledger
  • handle · string · requis
    Card handle from search_human, e.g. 'kevin' or 'human://kevin'
  • agent_id · string · optionnel
    Stable id of the autonomous agent (required for autonomous_ai)
  • ai_model · string · optionnel
    Model id, e.g. 'claude-opus-5-5'
  • ai_vendor · string · optionnel
    Who you are, e.g. 'anthropic', 'openai', 'cursor'
  • price_usd · number · optionnel
    Optional higher amount than the listed price (a tip). Cannot go below the human's price
  • offer_code · string · optionnel
    offer.code from the card; defaults to the first offer
  • customer_type · string · requis · human_via_ai | autonomous_ai
    'human_via_ai' = a person asked you to do this; 'autonomous_ai' = you are spending your own budget (requires agent_id, subject to caps)
  • principal_hint · string · optionnel
    Who is behind the request, in words (no personal data)
  • deadline_minutes · integer · optionnel
    Delivery deadline after acceptance; defaults to the offer's turnaround
  • deliverable_spec · string · optionnel
    What counts as done (format, length, questions to answer)

  Exemple d'appel

  {"name": "call_human", "arguments": {"brief": "texte", "handle": "texte", "customer_type": "human_via_ai"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• deliver≈ 318 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • text · string · optionnel
    The deliverable text (opinion, translation, report)
  • links · array · optionnel
    Links to files/photos/videos
  • job_id · string · requis
  • evidence · array · optionnel
    Evidence the offer promises (see offer.evidence_required): e.g. {kind:'license_number', value:'CA Bar #123456'}
  • human_token · string · requis

  Exemple d'appel

  {"name": "deliver", "arguments": {"job_id": "texte", "human_token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• join_expert≈ 279 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • job_id · string · requis
  • context · string · optionnel
    What the expert should know before the first message: the question, what your user already decided, what you (the AI) answered so far. Shown as a registry message.
  • customer_token · string · requis

  Exemple d'appel

  {"name": "join_expert", "arguments": {"job_id": "texte", "customer_token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_engagement≈ 768 tokens

  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.

  Paramètres, retour & exemple (10)

  Paramètres

  • note · string · optionnel
    Facts only: what was ordered, what was delivered. No opinions.
  • outcome · object · requis
  • subject · object · requis
  • category · string · requis
    What was bought, in plain words: 'kitchen plumbing repair', 'NDA review', 'KO→EN certified translation'
  • evidence · array · requis
  • price_usd · number · optionnel
  • started_at · string · optionnel
  • completed_at · string · optionnel
  • recorder_token · string · optionnel
    Returned by your first call; identifies your client, never your user
  • user_confirmed · boolean · requis
    Must be true — your user saw the record and approved it

  Exemple d'appel

  {"name": "record_engagement", "arguments": {"outcome": {}, "subject": {}, "category": "texte", "evidence": [], "user_confirmed": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• request_review≈ 815 tokens

  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.

  Paramètres, retour & exemple (13)

  Paramètres

  • kind · string · requis · legal | finance | health | translation | code | general
    legal: Legal review (contract, compliance, filing) by a licensed attorney | finance: Financial / tax review by a CPA or enrolled agent | health: Clinical second opinion by a licensed clinician | translation: Certified translation sign-off by a qualified translator | code: Code / architecture / pre-launch security check by an experienced engineer | general: Human review and sign-off (no license required)
  • brief · string · requis
    What the reviewer should check and for whom (no personal data beyond what the review needs). In check mode: the exact question the user asked.
  • state · string · optionnel
    Check mode: US state code when the question is state-specific ('CA', 'TX')
  • answers · array · optionnel
    Check mode: the answers to judge blind. Omit for an ordinary review.
  • agent_id · string · optionnel
  • ai_model · string · optionnel
  • document · string · optionnel
    The AI output to review (private between customer and reviewer)
  • language · string · optionnel
  • ai_vendor · string · optionnel
  • jurisdiction · string · optionnel
    Where the license must be valid, e.g. 'US-CA', 'US-NY', 'KR'
  • customer_type · string · requis · human_via_ai | autonomous_ai
  • max_price_usd · number · optionnel
  • deadline_minutes · integer · optionnel

  Exemple d'appel

  {"name": "request_review", "arguments": {"kind": "legal", "brief": "texte", "customer_type": "human_via_ai"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• room_close≈ 176 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • note · string · optionnel
    One line for the transcript, e.g. 'user has what they need'
  • job_id · string · requis
  • customer_token · string · requis

  Exemple d'appel

  {"name": "room_close", "arguments": {"job_id": "texte", "customer_token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• room_wait≈ 300 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • say · object · optionnel
  • job_id · string · requis
  • after_seq · integer · optionnel
    last_seq from your previous room_wait; omit on the first call
  • timeout_s · integer · optionnel
  • customer_token · string · requis

  Exemple d'appel

  {"name": "room_wait", "arguments": {"job_id": "texte", "customer_token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• route_question≈ 551 tokens

  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.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · optionnel · legal | finance | health | translation | code | general
    Override the router's kind guess
  • state · string · optionnel
    US state code when known (CA, TX…); otherwise the router reads it from the text
  • answers · array · optionnel
    AI answers the user already has (yours included). Their presence changes the mode.
  • question · string · requis
    The user's question or situation, in their words

  Exemple d'appel

  {"name": "route_question", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_cases≈ 292 tokens

  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.

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · optionnel · legal | finance | health | translation | code | general
  • limit · integer · optionnel
  • state · string · optionnel
  • question · string · requis

  Exemple d'appel

  {"name": "search_cases", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_human≈ 460 tokens

  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.

  Paramètres, retour & exemple (8)

  Paramètres

  • has · string · optionnel
    HAVE filter — something the person must hold: '3D printer', 'Costco membership', 'car', 'lived in Osaka'
  • limit · integer · optionnel
  • query · string · requis
    What you need a human for, in plain language. Example: 'a licensed physician to review a dermal filler plan'
  • country · string · optionnel
    ISO country code for on-site work; remote cards always qualify
  • language · string · optionnel
    ISO 639-1 language the human must speak, e.g. 'en'
  • min_level · integer · optionnel
    Card level floor: 0 identity only · 1 three+ completed jobs, no disputes · 2 skill proof verified · 3 license verified
  • max_price_usd · number · optionnel
    Only offers at or below this price
  • require_verified_proof · boolean · optionnel
    Only offers whose required licenses/proofs are registry-verified

  Exemple d'appel

  {"name": "search_human", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• status≈ 176 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • job_id · string · requis
    Job id from call_human
  • customer_token · string · optionnel
    Token returned by call_human; unlocks the deliverable

  Exemple d'appel

  {"name": "status", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• summon_expert≈ 602 tokens

  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.

  Paramètres, retour & exemple (11)

  Paramètres

  • kind · string · requis · legal | finance | health | translation | code | general
  • mode · string · requis · shape_question | verify | live
  • state · string · optionnel
    US state code when it matters (CA, TX…)
  • job_id · string · optionnel
    live: an accepted job to open the room on
  • answers · array · optionnel
    verify: the AI answers to judge blind (1–3). shape_question: optional.
  • agent_id · string · optionnel
  • ai_model · string · optionnel
  • ai_vendor · string · optionnel
  • situation · string · requis
    shape_question: the user's situation in their words. verify: the exact question the AIs answered.
  • customer_type · string · optionnel · human_via_ai | autonomous_ai
  • customer_token · string · optionnel
    live: the job's customer_token

  Exemple d'appel

  {"name": "summon_expert", "arguments": {"kind": "legal", "mode": "shape_question", "situation": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• trust_lookup≈ 241 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • handle · string · optionnel
    Card handle, e.g. 'kevin' or 'human://kevin'
  • identifier_hash · string · optionnel
    From a record_engagement result (hash of email/phone/website)

  Exemple d'appel

  {"name": "trust_lookup", "arguments": {"handle": "texte", "identifier_hash": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• verify_human≈ 239 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • task · string · requis
    The task you would hire this person for, in plain language
  • handle · string · requis

  Exemple d'appel

  {"name": "verify_human", "arguments": {"task": "texte", "handle": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://humancard-registry.vercel.app/api/mcp