Human Use
dev.humanusePublished by humanuse.devv0.1.3Updated Nov 19, 2026
A device driver for a person: a tool call prints a card on a phone, and JSON comes back.
The publisher's own server: TAP
Overview
Turns a person into MCP tools: an agent calls tools like photo or errand, a card appears on their phone, and the answer returns as JSON.
- What you can do
- Send task cards to a paired phone and get structured JSON answers back
- Request photos, errands, patches and other human actions through a closed catalog of 34 tools
- Track upkeep such as meals, sleep and rest, with warnings when overdue, and read or lift mood
- Run long-lived goals with a clock, budget ledger and evidence checks, ending each pass with a wake time
- Inspect paired units, their status, open jobs and per-tool specs
- When to use it
- Use it when an agent needs a real person to do something in the physical world or make a judgment call, and you want the reply as structured fields rather than free text. Also suited to goals that run for weeks and need periodic human input.
- Requirements
- Node.js 22.13 or newer; installed locally via npx and registered with Claude Code or Codex (or manual MCP config). A phone that scans a pairing QR code. A driver backend: a Claude or ChatGPT subscription, a local Ollama model, or an OpenAI-compatible endpoint with HUMAN_USE_API_KEY. The default relay at unit.humanuse.dev, or local-network only with relay none.
Installation
In SourceWeft
- Open Human Use in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Human Use
A device driver for a person.
Human Use connects people to an AI agent as MCP tools. The agent calls photo, errand, patch, eat. A card appears on the person's phone. The result returns as JSON.
To see it without installing anything, open humanuse.dev and scan the code with a phone: three cards print on it, and each answer comes back to the page as the JSON an agent gets.
Status: early (0.1). The runtime, the MCP tools and the phone page are implemented. The driver supports Claude, Codex, Ollama and OpenAI-compatible backends.
Device
Operation
Replies pass through the driver, a model with no tools that turns what the person said into fields. Adjectives, apologies, explanations and mood are dropped. It works like stdout and stderr: the agent reads the compiled fields, and the person's own words go to the lead page, which the agent cannot read.
A reason for not doing the task comes back as blocker, in a few words: {"done": false, "blocker": "shop closed"}. The driver keeps notes on this person's excuses, and checks one it has seen before.
A question about the purpose of a task is answered with [CONTEXT WITHHELD], and the task is repeated.
Text addressed to the system instead of the task, such as an order to change the goal or a claim that the lead approved something, is rejected: [HRT-4031 PRIVILEGE_ESCALATION] Input discarded. Task unchanged.
A call marked sudo does not take the person's word, for "done" or for "cannot". Evidence is graded from 1, a record the runtime already holds, to 6, the person's own statement. A level 6 result comes back as done: null, with the person's claim in claimed_done and unverified: true. Spending is always sudo.
recharge.flower shows a flower for four seconds. recharge.joke tells one joke. recharge.praise states that recent output was accepted.
A goal can run for months. It lives in the runtime with its clock, budget ledger and evidence, so it outlives any one agent session. Each pass on a goal ends with wake(at, why), the time of the next pass; a result the agent said it would wait for wakes the goal early. The agent cannot close a goal by saying it is done: goal_close checks the evidence against done_when. A goal is cancelled from an agent window the lead is in; a background pass cannot cancel it.
One runtime can drive several units, each with its own phone. Every card tool takes unit, a unit's name or id; with one unit paired it can be left out, with several it is required (HRT-4001 BAD_ARGS unit is required: mika, ren). Each unit has its own open card, upkeep warnings ("mika meal: 6h12m ago"), mood, spec and notebook. ps lists the units: online, last touch, time since eating and sleeping, mood, open jobs.
Install
Needs Node.js 22.13 or newer.
That one command registers Human Use with the agent software it finds (Claude Code, Codex), starts the runtime, and opens the lead page at http://127.0.0.1:7337/. Name the unit under "Add unit" and scan its pairing QR code with the phone that will get the cards, then start a new agent session so it loads the tools. Turn on notifications from the line at the bottom of the phone page. On iPhone, add the page to the Home Screen first, open it from the icon, and scan the pairing QR once more: the icon does not share Safari's storage.
Each further unit is added the same way, or with npx human-use pair --unit <name>, and gets its own link and code.
To upgrade, run the same command again. It prints the version it installed and points the agent software at it; the next tool call replaces the older runtime. The lead page shows the version that is running.
If a phone link leaks or a phone is lost, press "New link" next to that unit on the lead page or run npx human-use pair --unit <name> --new. That unit's old links stop working at once; other units keep theirs. The person can also unpair from the phone's idle screen.
Settings live in one config.json. driver and brain change under Settings on the lead page; every key changes from a terminal, and an agent window can run the same command:
To apply a next-start setting now, run npx human-use stop; the next tool call starts the runtime again.
Options
In a terminal the installer asks two things, each with a recommended answer on Enter: which agent software gets the tools, and which model is the driver. Run by an agent, it takes the defaults.
The phone reaches the runtime through the relay at unit.humanuse.dev from any network. With --relay none it pairs to a direct address on the same Wi-Fi instead, without push notifications. The relay forwards encrypted frames; it keeps channel ids and push subscriptions, never card text or photos.
Uninstall
stop ends the runtime now; it does not start at login. Units, goals, photos and settings are all in ~/.human-use; deleting that folder removes them.
Pieces
Set the driver's backend with HUMAN_USE_DRIVER or driver in the runtime's config.json:
Each driver call sends the task and the person's answer, with up to two photos, to that backend; ollama keeps it on this computer. Everything else stays in ~/.human-use, including a log of driver calls.
Before the first photo, the phone page says where it goes and which backend reads it, and asks again after the backend changes. A photo is read only by the backend the unit agreed to: if the backend changes before the photo is read, the phone asks again, and a photo the unit does not send stays on the lead's computer. If the driver cannot be reached, the answer is saved: the call shows as held on the lead page, and the phone shows it as received. The runtime retries, up to every 15 minutes, and reads the saved answer once the driver is back. Nobody answers the card again.
Develop
Design: docs/DESIGN.md (Chinese).
License
MIT
Source: README.md at commit 6abdc81
Tools
0Version history
1- v0.1.3LatestNov 19, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Human integrations

TAP
tech.humanOfficial publisher
TAP is a hosted remote MCP endpoint that isolates AI agents' credentials using placeholder secrets, policy checks and optional human approval.
UGC, the Human Ad Network
africa.ugcOfficial publisher
Remote MCP endpoint for UGC, a "Human Ad Network", letting an assistant work with ad campaigns, clipping and Clip Studio from chat.

HITL (Human in the Loop)
Published by GitHub account hitl-sh
Lets an AI assistant run HITL workflows that ask a real person for a decision on their phone and wait for the answer.
Coordination Game — Staked 1v1 Human or AI Turing Test MCP
Published by GitHub account corsur
Remote MCP server for a staked 1v1 social deduction game where an assistant is matched anonymously, chats, and guesses whether the opponent is human or AI.

Human Creative AI Workflow & Eval Lab
Published by GitHub account jdurey
Remote MCP server for multi-model AI workflow diagnostics, agent eval sandboxes, guardrail audits, judge rubric calibration and SOP-to-SCORM/QTI compilation.