# Vexa MCP server

> Send meeting bots into Google Meet, Teams and Zoom calls and read live or finished transcripts with labelled speakers.

- Listing: https://mcp.tc/i/vexa
- Connect: use the server's own URL `https://api.cloud.vexa.ai/mcp` (with your API key); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: API key
- Category: [Communication & Meetings](https://mcp.tc/c/communication)
- Vendor: Vexa-ai
- Homepage: <https://docs.vexa.ai/vexa-mcp>
- Repository: <https://github.com/Vexa-ai/vexa>

## About

Vexa is an open-source meeting transcription API. A bot joins Google Meet, Microsoft Teams or Zoom calls and produces speaker-attributed transcripts, live or after the call. The MCP server exposes these meeting capabilities as tools to an AI assistant. The docs list 21 tools on the hosted service and 17 in the open-source release.

The hosted endpoint uses streamable HTTP at api.cloud.vexa.ai/mcp and needs an Authorization header with a Bearer Vexa API key from the account page. Vexa can also be self-hosted with Docker (Apache-2.0 license).

## What it can do

- Send a bot into Google Meet, Teams or Zoom calls
- Read live transcripts with speaker labels
- Read transcripts after a meeting ends
- Use meeting content as context for an AI assistant
- Self-host the stack or use the hosted service

## Example prompts

- "Send a Vexa bot to my Google Meet call abc-defg-hij."
- "Show the transcript of my last Teams meeting."
- "Summarize what each speaker said in today's Zoom call."
- "What did we decide in my last meeting?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http vexa https://api.cloud.vexa.ai/mcp --header "Authorization: Bearer <YOUR_API_KEY>"
```

2. Replace the placeholder with your key before you run it, then check it with `/mcp` inside Claude Code.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Use the `mcp-remote` bridge, which keeps the key on this computer (a connector added on claude.ai with the key under **Request headers** also shows up here). Open **Settings → Developer → Edit Config** and add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "vexa": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.cloud.vexa.ai/mcp",
        "--header",
        "Authorization: Bearer <YOUR_API_KEY>"
      ]
    }
  }
}
```

2. Replace the placeholder with your key and restart Claude Desktop.

The bridge needs Node.js on your computer.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Vexa&connectorUrl=https%3A%2F%2Fapi.cloud.vexa.ai%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://api.cloud.vexa.ai/mcp`. Under **Request headers**, add `Authorization: Bearer <YOUR_API_KEY>` with your key from Vexa-ai, then click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=vexa&config=eyJ1cmwiOiJodHRwczovL2FwaS5jbG91ZC52ZXhhLmFpL21jcCIsImhlYWRlcnMiOnsiQXV0aG9yaXphdGlvbiI6IkJlYXJlciA8WU9VUl9BUElfS0VZPiJ9fQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "vexa": {
      "url": "https://api.cloud.vexa.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}
```

### VS Code

Add it to `.vscode/mcp.json`. VS Code asks for the key the first time and stores it securely:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "vexa": {
      "type": "http",
      "url": "https://api.cloud.vexa.ai/mcp",
      "headers": {
        "Authorization": "Bearer ${input:api-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "api-key",
      "description": "API key",
      "password": true
    }
  ]
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "vexa": {
      "serverUrl": "https://api.cloud.vexa.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add vexa --url https://api.cloud.vexa.ai/mcp --bearer-token-env-var VEXA_API_KEY
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.vexa]
url = "https://api.cloud.vexa.ai/mcp"
bearer_token_env_var = "VEXA_API_KEY"
```

Set `VEXA_API_KEY` to your key in the shell that runs Codex.

### Gemini CLI

```bash
gemini mcp add --transport http --header "Authorization: Bearer <YOUR_API_KEY>" vexa https://api.cloud.vexa.ai/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "vexa": {
      "type": "http",
      "url": "https://api.cloud.vexa.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.cloud.vexa.ai/mcp`.

## Details

- Server version: 0.12.27
- Last checked: 2026-10-07 (reachable, asks for credentials)
- Listed: 2026-10-04
- Updated: 2026-10-04

---
Source: https://mcp.tc/i/vexa (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report