mcpField
S
Speaking Bots MCP Server

Speaking Bots MCP Server

Local
speaking-bots-mcp.vercel.appCommunication0Updated 68w ago
RepositoryVisit website

About Speaking Bots MCP Server

Speaking Bots MCP Server is an open-source server for deploying voice agents in video meetings using MeetingBaas and Pipecat. It is intended for developers building customizable bots with persona, voice, and context settings.

Key features

  1. 01Join video meetings as a speaking bot
  2. 02Customize persona, voice, and context
  3. 03Stream audio bidirectionally in real time
  4. 04Generate persona images
  5. 05Remove bots from meetings

Use cases

  1. 01Deploy a bot to join a video meeting
  2. 02Configure distinct bot personas and voices
  3. 03Build voice or multimodal meeting agents
  4. 04Remove a bot from an active meeting

MCP support

The MCP server connects LLM-based voice agents to meeting capabilities and exposes bot operations, including joining and leaving meetings, through its API.

#speaking-bots#meeting-bots#ai-assistant

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "speaking-bots": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SEO_REVIEW_TOOLS_API_KEY",
        "mcp/seo-review-tools"
      ],
      "env": {
        "SEO_REVIEW_TOOLS_API_KEY": "<SEO_REVIEW_TOOLS_API_KEY>"
      }
    }
  }
}
Run commanddocker run -i --rm -e SEO_REVIEW_TOOLS_API_KEY mcp/seo-review-tools
Environment variables to set
SEO_REVIEW_TOOLS_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocimcp/seo-review-tools

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Join our Discord!

Speaking Bots MCP Server

Deploy AI-powered speaking agents in video meetings using the MeetingBaas API. This open-source MCP server demonstrates how to connect LLM-powered voice bots to Google Meet, Zoom, and Microsoft Teams, with customizable personas and real-time audio streaming.

Introduction

This project provides a minimal, production-ready API for deploying speaking bots in video meetings. It integrates with MeetingBaas and Pipecat's Python framework for building voice and multimodal conversational agents.

  • Join meetings as an AI speaking bot
  • Customizable personas and voices
  • Real-time bidirectional audio streaming
  • Minimalist, extensible API design

The API is open source and designed for easy customization and extension.

Getting Started

  1. Clone this repository
  2. Install dependencies
  3. Set your environment variables (see below)
  4. Run locally or deploy to your preferred platform (Docker, fly.io, Vercel, etc.)
Environment Variables
  • BAAS_API_KEY: Your MeetingBaas API key (required)
  • BAAS_URL: The MeetingBaas API base URL (required)
  • NODE_ENV, LOG_LEVEL: (optional)

API Reference

The Speaking Bot API is accessible at https://speaking.meetingbaas.com.

Example: Join a Meeting as a Speaking Bot
curl -X POST https://speaking.meetingbaas.com/bots \
  -H "Content-Type: application/json" \
  -H "x-meeting-baas-api-key: your-api-key" \
  -d '{
    "meeting_url": "https://us06web.zoom.us/j/123456789?pwd=example",
    "personas": ["baas_onboarder"]
  }'
Key Endpoints
  • POST /bots — Join a meeting as a speaking bot
  • DELETE /bots/{bot_id} — Remove a speaking bot from a meeting
  • POST /personas/generate-image — Generate a persona image

See the OpenAPI spec for full details and parameters.

Command Line Usage

You can interact with the API using curl or any HTTP client. See the example above for joining a meeting. For advanced usage, see the scripts directory (if present) or build your own CLI tools.

Personas System

Speaking bots can be assigned unique personas, each with their own context, voice, and characteristics. Personas are defined in Markdown or JSON and can be extended or customized.

  • Choose from a library of built-in personas (e.g., baas_onboarder, pirate_queen, quantum_physicist)
  • Generate custom persona images via the API
  • Control voice, language, and context for each bot

Directory Structure

api/                # API route handlers and tool registration
config/             # Core configuration and persona management
scripts/            # Command-line tools and utilities

Acknowledgements

Meeting BaaS

For more information about MeetingBaas and the SDK:

License

This project is open source and welcomes contributions. See LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.