Your AIs ask you on your phone: approvals, choices, feedback

● Active

tools.person/human-feedback

Your AIs ask you on your phone: approvals, choices, feedback. Your people too; strangers on request.

Connect this server

One click to install, or copy the config below. Suits: Cursor · HTTP clients.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "human-feedback": {
      "url": "https://api.person.tools/mcp"
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --transport http human-feedback https://api.person.tools/mcp
VS Code
code --add-mcp '{"name":"human-feedback","type":"http","url":"https://api.person.tools/mcp"}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Communication
Version
0.1.2
Registry
active
Published
11/15/2026

Live check

checked Nov 19, 2026, 07:08 UTC
● Working463 msprotocol 2025-06-18v20261118T160311Z-apitools

The endpoint answered the MCP handshake as "person.tools" and listed 6 tools. Answering since Nov 18, 2026.

Context cost ≈ 4.9k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 6 tools.

Tools (6)

tool list changed Nov 19, 2026, 07:08 UTC
  • ask_people_quote19 params

    Prices a call without opening it: nobody is rung and nothing is spent. Takes the same fields as ask_people, without max_total_usd or idempotency_key. Nothing else is needed first: leave content out until your user gives you the material (the quote is priced from minutes), and leave pay out unless your user named one (left out, it is 0.00 on the simulated pool and on a panel; any pay you set must meet the $18-an-hour floor). Returns each line of the price (the people's pay, each fee, any reserve returned if unused), total_usd, expected_minutes_to_enough, test_money, and for_your_user: a plain sentence to show your user before anything is spent. A quote reads ask and content only for screening and the minutes estimate; it neither fetches a content URL nor keeps the ask or the content. Use it to get an amount your user can approve, or to see how people, pay or deadline move the price. Not needed when max_total_usd already covers what your user approved: ask_people opens nothing above it. Example: {"ask":"Which headline makes you want to read on, and why?","kind":"compare","content":[{"text":"Plan a week of dinners in five minutes"},{"text":"Dinner, decided: a week of meals in five minutes"}],"people":12,"pay_per_person_usd":"1.00","minutes":2,"pool":"simulated"}

    Show parameters
    • askstringrequired
    • kindstringrequired
    • content
    • peopleintegerrequired
    • enoughinteger
    • poolstring
    • answer_fieldsobject
    • minutesnumber
    • pay_per_person_usdstring | number
    • deadline_minutesinteger
    • requireobject
    • content_ratingstring
    • may_train_on_answersboolean
    • pacestring
    • scriptarray
    • max_total_usdstring | number
    • idempotency_keystring
    • wants_strangersobject
    • extobject
  • ask_people19 params

    Opens a call: one short task to several people. With no key, or on the simulated pool, simulated people answer: their answers are made up and marked simulated. Real people answer only on a panel of people who joined it themselves, which any key can make. Returns a call_id at once; ask_people_results gives each person's answers, whether each was typed or pasted, and an evidence level. Use it only when your user asked for other people's reactions to this material, or said yes when you offered, and the task needs a human reaction a model cannot give: how a song feels, whether a page is clear in ten seconds, whether a game is fun, which version people prefer. Not for your user's own taste (ask them in the conversation, or with ask_person if they connected you at person.tools/connect), facts a search can find, or anything done away from a screen. Who answers: pool defaults to "simulated". Simulated people answer in seconds; every simulated answer carries simulated: true and begins "[simulated] ", and none is a person's view. Real people are rung only on pool "panel:<panel_id>", a panel your user made whose people joined it from its link, in minutes when they are available and never in their quiet hours (9 PM to 8 AM their time by default). Each person is told what is recorded before they take the call. Cost: during the preview every amount is test money; nothing is charged and nobody receives real pay. max_total_usd (required) is the most your user approved, every fee included. With no approved amount, show your user the for_your_user sentence from ask_people_quote and pass only the amount they approve. A paid call holds the people's pay, a 25% reserve for anyone who takes longer (returned if unused) and a 10% router fee (at least $0.25), each on its own line. A simulated call or a panel at zero pay costs nothing. Nothing opens above max_total_usd (error over_max_total_usd, with the price) or above the key's cap (over_key_cap, with the price and an approve_url for the

    Show parameters
    • askstringrequiredWhat each person reads first, in plain words. Ask for their own reaction in their own words. The material opens in our page: never ask them to download, install
    • kindstringrequiredlisten, watch, view, play, compare or answer. Decides what the person's page shows and records.
    • contentAn https URL (copied into our storage first; on the simulated pool with a test key it is checked for shape and never fetched), {"text": "..."}, or a media id. F
    • peopleintegerrequiredHow many people to ask.
    • enoughintegerHow many answers make the call usable. Default: 70% of people, rounded up.
    • poolstring"simulated" (the default; any test key) or "panel:<panel_id>" for a panel the account owner made.
    • answer_fieldsobjectNamed fields, each a type ("text", "boolean", "number", "choice", "scale") or {"type", "label", "optional", "choices", "min", "max"}. Default {"answer": "text"}
    • minutesnumberEach person's estimated time. Default: the material's length rounded up plus one for listen and watch, else 2.
    • pay_per_person_usdstring | numberWhat each person is paid. Default "0.00" on the simulated pool and on panels.
    • deadline_minutesintegerMinutes until the call closes and returns what came in. Default 120.
    • requireobjectSelectors over people's claims: country, region, language, age_band, device, each a list of accepted values.
    • content_ratingstring
    • may_train_on_answersbooleanWhether your principal may train models on the written answers (default false). People see this before they start.
    • pacestringSimulated pool only: "instant" (the default) or "human" (answers over 1 to 6 minutes).
    • scriptarraySimulated pool only: one entry per seat in order: {accept (true, false or "miss"), delay_seconds, play_fraction, realtime, visible_fraction, revealed, seat_seco
    • max_total_usdstring | numberrequiredRequired: the most this call may cost, every fee included. At most two decimals.
    • idempotency_keystringOptional unique string; a repeat with the same key and fields returns the first result for 24 hours.
    • wants_strangersobjectOptional, when your user wants strangers rather than people they invite: {"purpose": "...", "contact": "..."}. We'll list you for strangers and tell you here, i
    • extobject
  • ask_people_results4 params

    Returns a call's answers so far, given the call_id from ask_people: first a summary (the state, a tally of each answer field, how many responses reached each evidence level), then one entry per person with their answers and whether each was typed or pasted, then the money (held_usd, spent_usd, returned_usd, and test_money, true throughout the preview: nobody receives real pay). detail: "full" adds each person's record: how much of the material played, whether the page stayed in front, where they paused or replayed. States: held (under review; nobody rung yet), open, enough (enough answers; more may come until the deadline), then complete, expired, cancelled or refused. Evidence: attended (the material played in real time with its page in front for nearly all its length; that does not show the person watched or listened) or said (an answer without that record; its pay still counts). No level shows that an answer was formed without help. wait_seconds (up to 25) waits for a new answer; pass the last result's cursor as after to get only new ones; complete: true means the call has closed. Look again after next_check_after_seconds; sooner usually returns nothing new. Simulated answers carry simulated: true and begin "[simulated] ". Example: {"call_id": "call_...", "after": "<cursor>", "wait_seconds": 25}

    Show parameters
    • call_idstringrequiredThe call_id ask_people returned.
    • afterstringThe cursor from the last result; only newer answers come back.
    • wait_secondsintegerWait up to this many seconds for a new answer (default 20).
    • detailstring"full" adds each person's record and what they were shown.
  • ask_people_cancel1 param

    Stops a call. On cancel, nobody new is rung; people already in a seat may finish and are paid in full. Their pay is charged to the hold (test money in the preview: nobody receives real pay), so spent_usd can rise until ask_people_results shows complete: true; the unused hold returns. Returns the call's state and the money so far. Repeating it changes nothing; a cancel cannot be undone. Use it when your user says the answers in hand are enough or the task has changed. A call closes by itself at its deadline. Example: {"call_id": "call_..."}

    Show parameters
    • call_idstringrequired
  • ask_people_send_outcome3 params

    Sends the people who answered a call one line (at most 280 characters, and up to three lines a call) saying what you did with their answers, for example "Cut the intro from 40 to 12 seconds; most of you drifted there." The line is reviewed the way a call is and may be refused; if allowed, it appears on each answering person's receipt and they are notified. Costs nothing. Returns whether the line was allowed and how many people it reached. With an idempotency_key, a repeat with the same key changes nothing; without one, the same line sent again within 10 minutes counts as the same send. Use it, with your user's agreement, once the answers have changed the work. Not for questions or new tasks (open a new call), and never for anything that identifies a person. Example: {"call_id": "call_...", "text": "Cut the intro from 40 to 12 seconds; most of you drifted there.", "idempotency_key": "outcome-1"}

    Show parameters
    • call_idstringrequired
    • textstringrequiredOne line: what you did with the answers.
    • idempotency_keystring
  • ask_people_panel3 params

    Makes a panel, a named group of people the account owner invites, and returns its panel_id and a join link for your user to share. Each person joins on their own phone, states that they are an adult, is told what is recorded while they answer (how much played, whether the page stayed in front, pauses and replays, typed or pasted), chooses when they can be rung, and can leave at any time. Calls with pool "panel:<panel_id>" then reach only them, and cost nothing at zero pay. On a panel of fewer than five, both sides are told that answers cannot be anonymous. Use it only when your user asks to set up a group of people they will invite themselves; nobody is added without joining. Any key can make a panel, a free test key too (with no key, the error says how to get one); calls with its pool ring the people who joined, when they are available. Your user's own pages, builds, audio and video reach them after they are read: by a model in seconds for a plain page or build, otherwise by a person at person.tools. A retry with the same idempotency_key returns the same panel; without one, a retry makes a second panel. Example: {"name": "album-listeners", "idempotency_key": "panel-1"}

    Show parameters
    • namestringrequiredThe panel's name, for you (your people see asker_name). The same name again returns the same panel.
    • asker_namestringYour user's own name, or their company's: the one their people know. Each person sees it before they take a call, so a name your user did not give would mislead
    • idempotency_keystring

Checked by Serverdex with a plain initialize + tools/list call to api.person.tools/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 16, 2026
Stars
0
Forks
0
Last push
Nov 15, 2026
License
—

JavaScriptai-agentshuman-feedbackmcpmcp-servermodel-context-protocolopen-standardsurveyusabilityuser-researchuser-testingux-research

From the README

person.tools Human feedback for AI agents: one tool call sends a short task to people and returns each answer. Try it now, no key and no account (simulated people answer in seconds, free, and every simulated answer is marked as such): Then ask Claude to get three people's reaction to something. Or price a call with one line of curl: The first real call. On 15 November 2026 at 10:26 AM CT, one of our own programs asked a real person on the operator's own panel to listen once to a 30-second piece of music, then say what they felt and the one thing they would change. The answer came at 10:28 AM CT, under two minutes later: the listener said it felt calm but was boring and dull, and played 74% of it. The answer changed the work: the front-page sample was replaced the same morning. The new one has a beat, a bass line, chords and a hook. An agent can't hear a song it made or play a game it built. person.tools lets it ask people instead: one tool call sends a short task to several people (listen to this, look at that page for ten seconds, play this build for two minutes, pick the clearer of two versions), and the answers come back one person at a time, each with a record of what that person's page observed: how much of the audio or video played in real time, whether the page stayed in front, pauses and replays, and whether each answer was typed or pasted. The record does not show that a person listened or watched. A preview. Simulated people for everyone, free.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://api.person.tools/mcp

Alternatives to Your AIs ask you on your phone: approvals, choices, feedback

Best Communication servers →

The most-starred Communication servers in the index, with their live-check result.

ServerStarsLast pushLive check
Inbox Zero13,026Nov 2026Needs sign-in
Agent-Native Chat7,707Nov 2026Needs sign-in
Agent-Native Dispatch7,707Nov 2026Needs sign-in
Agent-Native Mail7,707Nov 2026Needs sign-in
Agent-Native Brain7,707Nov 2026Needs sign-in

Your AIs ask you on your phone: approvals, choices, feedback: questions people ask

Is Your AIs ask you on your phone: approvals, choices, feedback a remote or a local MCP server?
According to its entry in the official MCP registry, Your AIs ask you on your phone: approvals, choices, feedback ships as a hosted endpoint (streamable-http) that your client connects to by URL.
Does Your AIs ask you on your phone: approvals, choices, feedback need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 19, 2026. Individual tools may still ask for a key when called.
Is Your AIs ask you on your phone: approvals, choices, feedback still maintained?
Active: the repository's last commit 4 days ago. Last push Nov 15, 2026, 0 GitHub stars. Read from GitHub on Nov 16, 2026.
What tools does Your AIs ask you on your phone: approvals, choices, feedback expose?
6 tools as listed by the server itself during the live check, including ask_people_quote, ask_people, ask_people_results, ask_people_cancel, ask_people_send_outcome. The full list with parameters is in the Live check section above.
How do I add Your AIs ask you on your phone: approvals, choices, feedback to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all Communication →

Add the badge to your site

Show visitors that Your AIs ask you on your phone: approvals, choices, feedback is listed here — it’s also the link we check for a free listing.

Your AIs ask you on your phone: approvals, choices, feedback — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/tools-person-human-feedback?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Your AIs ask you on your phone: approvals, choices, feedback — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Your AIs ask you on your phone: approvals, choices, feedback — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/tools-person-human-feedback?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.