# Vexa

Sends a bot into Google Meet, Teams or Zoom calls and returns speaker-labelled transcripts, live or after the fact.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 2906
- Author: Vexa-ai
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Vexa-ai/vexa
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/vexa

## What it does

Vexa is an Apache-2.0 project. A bot joins the call as a participant, and the transcript comes back with each speaker labelled. The MCP server exposes that to your agent in Claude, Codex, Cursor, GitHub Copilot, Windsurf, Cline and Zed. If all you want is the transcript API, it stands on its own — the agent side is optional.

You can run the whole stack yourself: `git clone https://github.com/Vexa-ai/vexa.git`, then `make all`. Docker Compose brings the services up, seeds `.env` and prints your key plus the URLs. You need `make` and Docker engine v26 or newer. Speech-to-text needs either a token or your own GPU unit for transcription. With no STT, `POST /bots` answers 503, since transcription is on by default; turning it off is explicit — `{"transcribe_enabled": false}` on the spawn, or `TRANSCRIBE_ENABLED=false` for the deployment.

The hosted service at vexa.ai covers meetings and transcription only. Sandboxed agents that commit meeting outcomes into a Markdown repo exist in the self-hosted setup alone. Jitsi is proven offline for now, with live validation still pending.

## Requirements
- Needs: Docker
- Remote server: `https://api.cloud.vexa.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http vexa https://api.cloud.vexa.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add vexa --url https://api.cloud.vexa.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "vexa": {
            "url": "https://api.cloud.vexa.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "vexa": {
            "type": "http",
            "url": "https://api.cloud.vexa.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http vexa https://api.cloud.vexa.ai/mcp
```

## When to use it
- get a bot into a live call and pull the transcript
- label each line with the right speaker
- follow a transcript while the meeting runs
- ask an agent about decisions from past meetings
- commit meeting outcomes into a Markdown repo

## Example prompts
- Send a Vexa bot to the Google Meet call `abc-defg-hij`
- Show me the transcript from my last call with speaker labels
- Ask the agent what we decided in the previous meeting

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md