A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Human Capability Registry is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Search, hire and pay a verified human per job from any AI. Humans are handles; AIs call them.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http human-capability-registry-mcp https://humancard-registry.vercel.app/api/mcp
# 2 — ask your agent for something these tools do
# search_human, call_human, status and 13 more
Human Capability Registry costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HRAll 1 server
humancard-registry1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http human-capability-registry-mcp https://humancard-registry.vercel.app/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | What you need a human for, in plain language. Example: 'a licensed physician to review a dermal filler plan' |
| max_price_usd | number | no | Only offers at or below this price |
| language | string | no | ISO 639-1 language the human must speak, e.g. 'en' |
| country | string | no | ISO country code for on-site work; remote cards always qualify |
| require_verified_proof | boolean | no | Only offers whose required licenses/proofs are registry-verified |
| min_level | integer | no | Card level floor: 0 identity only · 1 three+ completed jobs, no disputes · 2 skill proof verified · 3 license verified |
| has | string | no | HAVE filter — something the person must hold: '3D printer', 'Costco membership', 'car', 'lived in Osaka' |
| limit | integer | no | — |
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 re
| Parameter | Type | Required | Notes |
|---|---|---|---|
| handle | string | yes | Card handle from search_human, e.g. 'kevin' or 'human://kevin' |
| offer_code | string | no | offer.code from the card; defaults to the first offer |
| brief | string | yes | What exactly you need. Private between customer and human; never shown on the public ledger |
| deliverable_spec | string | no | What counts as done (format, length, questions to answer) |
| deadline_minutes | integer | no | Delivery deadline after acceptance; defaults to the offer's turnaround |
| price_usd | number | no | Optional higher amount than the listed price (a tip). Cannot go below the human's price |
| customer_type | string | yes | 'human_via_ai' = a person asked you to do this; 'autonomous_ai' = you are spending your own budget (requires agent_id, subject to caps) |
| ai_vendor | string | no | Who you are, e.g. 'anthropic', 'openai', 'cursor' |
| ai_model | string | no | Model id, e.g. 'claude-opus-5-5' |
| agent_id | string | no | Stable id of the autonomous agent (required for autonomous_ai) |
| principal_hint | string | no | Who is behind the request, in words (no personal data) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job id from call_human |
| customer_token | string | no | Token returned by call_human; unlocks the deliverable |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
| human_token | string | yes | — |
| text | string | no | The deliverable text (opinion, translation, report) |
| links | array | no | Links to files/photos/videos |
| evidence | array | no | Evidence the offer promises (see offer.evidence_required): e.g. {kind:'license_number', value:'CA Bar #123456'} |
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 wh
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | yes | 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 | trans |
| brief | string | yes | 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. |
| document | string | no | The AI output to review (private between customer and reviewer) |
| answers | array | no | Check mode: the answers to judge blind. Omit for an ordinary review. |
| state | string | no | Check mode: US state code when the question is state-specific ('CA', 'TX') |
| jurisdiction | string | no | Where the license must be valid, e.g. 'US-CA', 'US-NY', 'KR' |
| language | string | no | — |
| max_price_usd | number | no | — |
| deadline_minutes | integer | no | — |
| customer_type | string | yes | — |
| ai_vendor | string | no | — |
| ai_model | string | no | — |
| agent_id | string | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| handle | string | no | Card handle, e.g. 'kevin' or 'human://kevin' |
| identifier_hash | string | no | From a record_engagement result (hash of email/phone/website) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| handle | string | yes | — |
| task | string | yes | The task you would hire this person for, in plain language |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| handle | string | yes | — |
| question | string | yes | — |
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 (use
| Parameter | Type | Required | Notes |
|---|---|---|---|
| recorder_token | string | no | Returned by your first call; identifies your client, never your user |
| subject | object | yes | — |
| category | string | yes | What was bought, in plain words: 'kitchen plumbing repair', 'NDA review', 'KO→EN certified translation' |
| started_at | string | no | — |
| completed_at | string | no | — |
| price_usd | number | no | — |
| outcome | object | yes | — |
| evidence | array | yes | — |
| note | string | no | Facts only: what was ordered, what was delivered. No opinions. |
| user_confirmed | boolean | yes | Must be true — your user saw the record and approved 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | — |
| context | string | no | What you tried, what is at stake (no personal data) |
| reward_usd | number | no | — |
| ai_vendor | string | no | — |
| ai_model | string | no | — |
| agent_id | string | no | — |
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 p
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
| customer_token | string | yes | — |
| context | string | no | 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. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
| customer_token | string | yes | — |
| say | object | no | — |
| after_seq | integer | no | last_seq from your previous room_wait; omit on the first call |
| timeout_s | integer | no | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
| customer_token | string | yes | — |
| note | string | no | One line for the transcript, e.g. 'user has what they need' |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | yes | — |
| kind | string | yes | — |
| situation | string | yes | shape_question: the user's situation in their words. verify: the exact question the AIs answered. |
| answers | array | no | verify: the AI answers to judge blind (1–3). shape_question: optional. |
| state | string | no | US state code when it matters (CA, TX…) |
| job_id | string | no | live: an accepted job to open the room on |
| customer_token | string | no | live: the job's customer_token |
| customer_type | string | no | — |
| ai_vendor | string | no | — |
| ai_model | string | no | — |
| agent_id | string | no | — |
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 × t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | The user's question or situation, in their words |
| answers | array | no | AI answers the user already has (yours included). Their presence changes the mode. |
| state | string | no | US state code when known (CA, TX…); otherwise the router reads it from the text |
| kind | string | no | Override the router's kind guess |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | — |
| kind | string | no | — |
| state | string | no | — |
| limit | integer | no | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Human Capability Registry or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 0.9.0 · scanned 21 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestd7235434f5cb5803a34ac9bf6cd075781601a8f277453e76640985070f85dba4
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_human | no tags | |
| call_human | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| status | no tags | |
| deliver | state-write | state-write: declares readOnlyHint: false |
| request_review | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| trust_lookup | no tags | |
| verify_human | no tags | |
| ask_card | no tags | |
| record_engagement | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| ask_human | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| join_expert | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| room_wait | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| room_close | state-write | state-write: declares readOnlyHint: false |
| summon_expert | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| route_question | no tags | |
| search_cases | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestd7235434f5cb5803
Scanned2026-10-21
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.9.0.
0.9.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Human Capability Registry can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.