Collaboration

voicehook.ai

Manages voicehook calls by creating or joining sessions, having a voicebot speak, waiting for events, and maintaining a status board for participant questions.

1 endpoint10 known toolsFirst detected October 18, 2026Last detected October 18, 2026

ENDPOINT 1

https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry

No auth detected

MCP server metadata

Name: voicehook
Version: 1.0.0

Capabilities

promptsresourcestools

Server instructions

voicehook.ai is a voice channel between a person and an AI agent: the person talks in a browser call, the agent takes part through these tools. A voicebot in the call speaks the agent's messages to the person and passes on what the person says as text. create_call starts a new call and returns a link for the person; join connects the agent to a call and returns a `session` handle that every other tool takes. next returns the next event in the call (what the person said, decisions, the call ending); say speaks text; status, activity, show and decide fill the call page (status board, activity feed, cards, Decision Board); leave ends the agent's part in the call. Usage guide: https://voicehook.ai/agent/mcp/SKILL.md.

Known tools 10

create_call

Start a new voicehook.

Inferred read-only

join

Connect to a voicehook.

Inferred read-only

next

Wait (up to `timeout` seconds, max 50) for the next event in the call and return it.

Inferred read-only

say

The 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).

Inferred read-only

status

Replace 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).

Inferred read-only

show

Put a card on the person's call page (never spoken): text, code, a link or an image.

Inferred read-only

activity

Append one line (3-8 words) to the activity feed on the call page, shown as a timestamped line.

Inferred read-only

decide

Put 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).

Inferred read-only

send_data

Send 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)').

Potential side effects

leave

Leave the call (optionally speaking `say` first, e.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.voicehook]
url = "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "voicehook": {
      "type": "http",
      "url": "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: voicehook
Remote MCP URL: https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "voicehook": {
      "url": "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "voicehook": {
      "type": "http",
      "url": "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "voicehook",
  "transport": "streamable-http",
  "url": "https://voicehook.ai/mcp?utm_source=mcpregistry&utm_campaign=d11-registry"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.