This is an MCP for sending and managing meeting bots with Attendee, an open-source meeting bot for recording and transcription. You can run Attendee locally or deploy it to the cloud.
Questions? Join the Attendee Slack.
Using Claude as an example: You can type the following and start working with an AI meeting bot.
- "Send a bot to this meeting: <meeting_url>"
- "Have the bot speak 'Hello'", and the bot would say 'Hello' it in the meeting.
- "Have the bot send a chat message: 'Glad to be here'", and the bot would write 'Glad to be here' in the chat.
- "Have the bot leave the meeting"
Combining MCPs leads to powerful workflows. For example, I use the Brave Search MCP alongside the Attendee MCP. When I ask Claude, “Who won the last Roland Garros tournament?”, it:
- Uses the web MCP to find the answer online.
- Pipes the result to the Attendee bot, which speaks the answer back to me
We will use Claude as an example, but you can use any tool that works with MCPs.
# Clone your fork or the main repo
git clone https://github.com/rexposadas/attendee-mcp.git
cd attendee-mcp
# Install dependencies
npm install
# Build the TypeScript
npm run build
# Link for global use
npm link
Set these environment variables for your Attendee server:
export MEETING_BOT_API_URL="http://localhost:8000" # Your Attendee server URL
export MEETING_BOT_API_KEY="your-api-key-here" # Your Attendee API key
Add these to your shell profile (~/.zshrc
, ~/.bashrc
, etc.) to make them permanent.
Update your Claude Desktop configuration file at:
~/Library/Application Support/Claude/claude_desktop_config.json
. after you make the changes, restart Claude
Adjust the mcpServers
section to include the Attendee MCP server. Use the direct path for now since that's proving to be the most reliable.
{
"mcpServers": {
"attendee": {
"command": "node",
"args": [
"<path>/attendee-mcp/dist/index.js"
],
"env": {
"MEETING_BOT_API_URL": "<attendee-url-here>",
"MEETING_BOT_API_KEY": "your-api-key-here"
}
}
}
}
Replace /path/to/attendee-mcp
with the actual path where you cloned the repository.
- Start your Attendee server:
make build make up
- Test in Claude Desktop:
- Ask Claude: "What MCP tools are available?"
Once configured, you can use natural language commands in Claude Desktop:
- "Create a meeting bot for this Zoom: https://zoom.us/j/123456789"
- "Send a bot to this Google Meet: https://meet.google.com/abc-defg-hij"
- "Join this Teams meeting with a bot: https://teams.microsoft.com/..."
- "What's the status of bot bot_abc123?"
- "Remove bot bot_abc123 from the meeting"
This server provides the following tools:
create_meeting_bot
- Create a bot to join and record a meetingget_bot_status
- Check the current status of a meeting botremove_meeting_bot
- Remove a bot from a meeting
make_bot_speak
- Make the bot speak using text-to-speechsend_chat_message
- Send chat messages from the botsend_image_to_meeting
- Display images through the bot (Google Meet only)send_video_to_meeting
- Play videos through the bot (Google Meet only)
get_meeting_transcript
- Retrieve the meeting transcriptget_chat_messages
- Get chat messages from the meetingget_recording
- Get the recording download URLdelete_bot_data
- Permanently delete all bot data
-
"Network error" or API connection issues:
- Ensure your Attendee server is running on the configured URL
- Check that your API key is correct
- Verify the
MEETING_BOT_API_URL
andMEETING_BOT_API_KEY
environment variables
-
MCP server not appearing in Claude Desktop:
- Restart Claude Desktop completely after config changes
- Check the Claude Desktop config file syntax is valid JSON
- Look at Claude Desktop logs for error messages
-
"Method not allowed" errors:
- Some API endpoints might not be fully implemented in your Attendee server
- Check your Attendee server logs for more details
MIT License - see LICENSE file for details.
- Fork the repository
- Create a feature branch:
git checkout -b feature-name
- Make your changes and test them
- Commit your changes:
git commit -m 'Add feature'
- Push to the branch:
git push origin feature-name
- Submit a pull request
- Attendee - The main meeting bot service
- Model Context Protocol - The MCP specification and SDK
Note: This MCP server requires a running Attendee backend service. Make sure you have the Attendee server set up and running before using this MCP server.