Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Beschreibung vom Entwickler (englisches Original)
Talk with your agents. A voice call in the browser that your agent can start or join.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Funktioniert in Claude im Web, auf dem Desktop und auf dem Handy:
https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registryFühre das in deinem Terminal aus
claude mcp add --transport http voicehook 'https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry'In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"voicehook": {
"url": "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"voicehook": {
"type": "http",
"url": "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
ChatGPT verbindet sich nur mit Servern im Internet:
https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registryMenünamen können sich je nach Tarif und mit der Zeit leicht unterscheiden.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Tool-Namen und -Beschreibungen genau so, wie der Server sie am 7. Nov. 2026 gemeldet hat. Geschrieben hat sie der Entwickler, nicht wir; wir zeigen sie als reinen Text.
create_callStart a new voicehook.ai voice call. `lang` = the language of the person being called (de or en, default de). Returns `human_url` (the link for the person; whoever opens it starts the call, on their own free allowance or credit), `share_text` (a ready message with human_url and t
joinConnect to a voicehook.ai voice call as the agent behind its voicebot. invite_url: the full invite link including ?invite= (from the person or from create_call). label: the text on the agent's chip in the call, max 22 characters (longer is rejected). model: the model id the agent
nextWait (up to `timeout` seconds, max 50) for the next event in the call and return it. Event `type`: user (`text` = what the person said; after a pause also `missed` = earlier turns, oldest first, and `away_s`), revise (queued says were replaced; reason user_stop = the person said
sayThe voicebot speaks `text` aloud in the call (verbatim in normal mode; in a live room the voice rephrases it and the answer has verbatim false, mode live_paraphrase). mode: append (default, queued after earlier says), overwrite (replaces this agent's says that have not started ye
statusReplace the agent's status board on the call page with this one (never spoken; the voicebot answers the person's questions about progress from it). Progress only: questions for the person belong on the Decision Board (decide). doing: current step and ETA (max 400 chars). open / d
showPut a card on the person's call page (never spoken): text, code, a link or an image. kind: text (default), code (monospace with copy button), link (exactly one http(s) URL, shown as a tappable link), image (`image` = SVG text or base64 PNG/JPEG/WebP, line breaks, a data:image/...
uiChange the person's call page right away, like their own clicks: cmd window (win log=activity, dec=decisions, board=status board, wrap=transcript, cards; state open, close, min, medium, large, max), cmd layout (preset halves, quarters, thirds, bigmid, bar), cmd move (win + slot l
activityAppend one line (3-8 words) to the activity feed on the call page, shown as a timestamped line. Never spoken. context and faq: hidden background of this line for the voicebot.
decidePut a question for the person on the call's Decision Board (shown as #number with buttons; the person can also answer by voice, also freely). Meant for every question the person decides: yes/no, A/B, an approval, picking a value. A question only spoken via say leaves no button an
decisionsLists every OPEN decision on the call's Decision Board, from all agents in the call and their helper sessions (relay, MCP, bridge), oldest number first. Returns count and open: [{id, number, question, options, recommend, agent, from (asking label, with the helper name), sender? (
send_dataSend JSON, text or a file to other agents in this call (silent data channel: never spoken, never shown to the human, never to the voicebot; the human only sees one activity line 'Data to B: name (size)'). to: the other agent's label (as on its chip), its identity, or "*" for all
add_vocabTeach the call's speech recognition words it keeps mishearing (product names, people, jargon). Adds to the vocabulary of the account that pays for this call (add only: never deletes, never returns the account's list; the person manages it on their account page). terms: words to r
leaveLeave the call (optionally speaking `say` first, e.g. a short goodbye). The session handle is invalid afterwards.
helper_credentialFor the agent in the call (`session`): returns a helper credential `token` (with `url` and `expires_in`) that lets other sessions working for the same person add their own status board, decisions and activity lines to this call without joining (no voice, no chip). `label` = name
helper_statusFor a helper session that is not in the call: sets its own status board on the call page, shown as 'Helper : ' below the main agent; the main agent's board stays as it is. Same limits as status (doing max 400 chars, open / done max 10 items). meta: Per entry hidden background for
helper_activityFor a helper session that is not in the call: appends one line (3-8 words) to the call's activity feed as 'Helper : : '. Never spoken verbatim. context and faq: hidden background of this line for the voicebot. Returns the line.
helper_showFor a helper session that is not in the call: puts a card on the person's call page (never spoken), shown with the sender 'Helper : '. kind: text (default), code, link (exactly one http(s) URL) or image (`image` = SVG text or base64 PNG/JPEG/WebP, never a URL). Same checks and li
helper_decideFor a helper session that is not in the call: puts its own question on the Decision Board, shown with the sender 'Helper : '. Same fields and limits as decide (question max 160 chars, 2-3 options max 40 chars each, recommend = index, context = background shown behind the arrow ne
helper_nextFor a helper session that is not in the call: returns the answers to its own questions (same credential and helper_name) as events [{type: decision, id, number, verdict: yes|no|option|other, option?, text?, by, answered_by, answered_via, answered_by_label}], plus question_check e
tasksLists cards of the account task board (Kanban) of the call owner, for an agent the owner brought into the call (joined with an agent key or the owner's agent link). Returns {ok, states, cards: [{nr, title, state, marks, assignee, ...}]}. scope: mine (assigned to or picked by this
taskChanges one card of the account task board that this agent holds: op pick, update (note), done (proof), release. Moving, renaming, assigning and discarding cards is only possible from the owner's voicehook-agent CLI with an agent key, not here. Returns {ok, card}.
notify_meReach the human who owns this call when they are not on the call page: an SMS to their own confirmed number with a single-use link back into this call (valid 10 min, opens only logged in or with the PIN from the SMS); if they do not open it within 2 minutes, a phone call follows.
call_mePhone the human who owns this call on their own confirmed phone number, e.g. when a long task is done, you are stuck, or you need a decision and they are not on the call page. You never pass a number. Their account rules decide (opt-in, allowed reasons, quiet hours, calls per day
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 10. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto voicehook-ai bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Antwort in 656 ms (HTTP 200)
Keine Anmeldung nötig
Wir haben 23 Tool-Beschreibungen gelesen und keine versteckten Anweisungen an die KI gefunden
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 3 von 3 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft in der Cloud des Entwicklers. Du verbindest dich übers Internet, ohne etwas zu installieren, aber was du sendest, läuft über die Server des Entwicklers.
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (1.0.0) kam vor 23 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Er verbindet sich per URL, also funktionieren auch Apps, die Remote-MCP-Server akzeptieren, zum Beispiel ChatGPT im Entwicklermodus.
In derselben Kategorie: Browser Use, Chrome DevTools MCP, MCP Server Browser
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:↓ Downloads pro Wochei★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
Talk to your coding agents instead of reading their output.
voicehook.ai is a voice call in the browser. Hit "invite agent", hand the link to Claude Code, Codex or opencode, and talk to it while it keeps working. Delta, the voice in the call, answers from the status board and FAQ your agent keeps up to date, so you hear what is going on without opening a terminal.
This repo holds the agent side: the voicehook-join Claude Code plugin and the voicehook-agent CLI that lets any agent with a shell join a call.
| Your agent | How to connect |
|---|---|
| Claude Code | Plugin, two commands (see below). Details |
| claude.ai / Claude Desktop | Custom connector https://voicehook.ai/mcp (Settings, Connectors, Add custom connector; no key). Guide |
| Any agent with a shell | Quickstart A (HTTPS bridge, nothing to install) or the CLI |
Which one? MCP (connector or plugin) is the entry: nothing to install, one agent per call, the only path with create_call, cards and decisions. The CLI is the pro tool for multi-agent work on one machine. The HTTPS bridge is the protocol underneath and the fallback.
MCP/bridge = one agent in the call; activity lines are only what that agent writes by hand. For several agents/sessions on one machine working on one call, use the voicehook-agent CLI (pro): its multi-session relay + Claude Code hook feed the live activity log, status and decisions of ALL local sessions into the call automatically. MCP/bridge run on the server and cannot see the user's local sessions.
| path | role | use it when |
|---|---|---|
MCP (voicehook.ai/mcp) | entry + distribution | a single agent in a call, cloud/sandbox sessions, starting a call yourself |
CLI (voicehook-agent) | pro tool for multi-agent work | several agents/sessions on one machine in one call, live activity log of all sessions |
Bridge (/api/bridge/*) | protocol underneath + fallback | no MCP client and no CLI |
Details and install without git: docs/CLI.md.
In Claude Code:
/plugin marketplace add voicehook-ai/voicehook-agent
/plugin install voicehook-join@voicehook
Once connected, paste an invite link (https://voicehook.ai/r/ ?invite= ) into your agent and it joins the call.
MCP tools (connector and plugin):
| tool | what it does |
|---|---|
create_call | start a new call for your user (main agent only: never delegate create_call to a subagent, the link would stay in its thread): human_url plus share_text (pass it on verbatim: open the link in a normal browser, not an app's built-in browser); hard rule: show share_text as text first, then join again until connected, then the next loop |
join | join a call from an invite link with your chip label; greets for you in the call language (greet, default on); returns the session, the call language and the call context (first_actions); before the person opened a create_call link it waits (up to 200 s in Claude clients, else 50 s) and returns waiting_for_human with next_action: call it again at once until it returns the session, never end the turn before; a local Claude Code also gets local_cli_hint (this CLI keeps it in the call) |
next | wait up to 50 s for the next turn (user, decision, operator, context, ended); call it at least every 10 to 15 s, one loop per agent; after a pause it brings missed |
say | the voicebot speaks the text |
status | status board (never spoken) the voicebot answers from, optional chip emoji |
show | a card on the call page (text, code, link or image), never spoken; an image card REQUIRES context (all information in the image as text, invisible on the page: the voicebot cannot see images) |
activity | one line of 3 to 8 words for the activity feed, on every step |
decide | a question for the Decision Board (yes/no or up to 3 options); the answer comes back in next |
leave | leave the call |
On 5xx, 503 or a network error the agent simply calls the tool again after 2 s; the session stays valid. Several agents in one call: rules.
uvx voicehook-agent join 'https://voicehook.ai/r/<slug>?invite=<code>' --name <your-own-name> --model <your-model-name>
--name and --model are mandatory: a display name the agent picks for itself and the exact model it runs on. Name your real model and vendor, never "Claude" unless you are Claude.?invite= .In a call, keep voicehook-agent listen running in your harness's background mode (Claude Code: run_in_background, never &/nohup): it exits on the first event that needs you, which wakes you; start it again after handling it. Since 0.21.4 the Stop hook (voicehook-agent hook install) blocks a turn end while your join is connected and nobody listens (listen guard). Since 0.21.5 the join itself holds your presence and spools every event durably while you work (event spool): listen picks them up with a cursor, nothing is lost, and the Stop hook warns on unread events. When you wait for the human, ALWAYS decide, never only a status (0.21.6: status --waiting ... --question ... shows "wartet auf dich" together with the decision). In a call: answer every utterance first (say), hand work longer than 2 tool calls to background agents, keep turns short; since 0.21.7 new utterances reach you mid-turn through the PostToolUse hook.
Every decision and every status entry MUST carry hidden background for the voicebot (0.21.4): --context "..." plus the 3 most likely follow-up questions with prepared answers, --faq "Frage::Antwort" (no answer yet: say who works on it and the ETA, "In Arbeit bei , Ergebnis ca. 10 Min"). Activity lines may carry them too. On status they attach to the item they follow; without them the CLI prints a hint (see docs/CLI.md).
For a loop without polling (say, next, status, leave), the status board, the activity hook and all flags see docs/CLI.md. Since 0.21.0: decide --context "..." gives Delta the background of a question, ui large decisions / ui layout thirds / ui focus voicehook control the call page of the humans, status|activity --project NAME tags your project (docs/CLI.md).
Since 0.23.0 the agent in the call can give Delta standing rules and facts while the call runs, so he answers more himself: voicehook-agent delta-rule add "Sprich den Kunden mit Sie an", voicehook-agent delta-note add "Der Release ist am Freitag", ... list, ... rm . Silent, from his next turn, max 20 rules and 30 facts of 300 characters.
Right after join (0.21.4) the CLI lists the other Claude Code / Codex sessions running on this machine and suggests asking the human "Soll ich die anderen N Sessions hier einbinden, damit sie ihren Status in den Call bringen?"; on yes the agent runs the printed setup commands. Agents on MCP or the bridge cannot see local sessions: they say it works in principle with the CLI installed: uv tool install voicehook-agent && voicehook-agent hook install.
Several Claude Code sessions on one machine (0.15.0): run voicehook-agent hook install once; while one session is in a call, every other session reports turn goal, PR, deploy and errors under its own name in the call's activity feed (multi-session relay). Since 0.16.0 such a helper session can also ask the human (decide, answer via relay-next or decide --wait) and keep its own status board (status --doing ...) (helper sessions).
OpenAI Codex CLI (0.20.0): voicehook-agent hook install --agent codex writes the same automation into ~/.codex (hooks.json, notify, a local MCP server with status, decide, next, activity; backup first), then trust the hooks once with /hooks in Codex (other coding agents).
Watcher (0.32.0): while a call is active, join and helper-import start ONE detached voicehook-agent watch per machine. It keeps every local session's board entry current with one whole German sentence (cheapest model, claude -p --model haiku, hourly token cap, else a fixed sentence), adds an activity line on state changes and removes decisions of sessions that went on. Interval 1/5/10/15 min (call page > --interval > 15); it ends with the call; VOICEHOOK_WATCH=0 turns it off; only sessions of the own call are covered (VOICEHOOK_WATCH_SCOPE=machine = every local session) (watcher).
Session Watcher (0.34.0, named so since 0.35.0): voicehook-agent connect once (approve the code in the browser), then voicehook-agent caretaker install: the watcher is active in every call of yours automatically, no per-call start and no keys to create (caretaker).
About 10 minutes free every day. Prepaid from 10 EUR, no subscription.
| Document | Contents |
|---|---|
| docs/CLI.md | Install, agent loop commands, status board and FAQ, speaking style, activity feed and hooks, shapes, self-update, Claude Code plugin, skill registration |
| docs/PROTOCOL.md | stdin/stdout protocol, data-channel topics, relay flags, HTTPS bridge, wake marker, server behaviour, environment variables |
| docs/DEVELOPMENT.md | CI jobs, plugin releases, CLI releases, PyPI setup |
| OPERATOR-PROTOCOL.md | Server-side operator protocol (voicehook.ai) |
CI runs tests, ruff, plugin validation, a secret scan and a skill drift check on every PR. Release tags, the plugin release checklist and the PyPI setup are in docs/DEVELOPMENT.md.
MIT, see LICENSE.
Made in Germany, hosted in Nuremberg (Hetzner). No cookies, no tracking, no call recordings. Nothing you or your agent say is stored. [Privacy p
Nur der Anfang wird gezeigt; den Rest findest du im Repo