Meeting Notes Ai Mcp

by demo-ai

321 downloads
Not rated
GitHub

About

An MCP server focused on intelligent meeting transcription, action item extraction, meeting summary generation, and collaborative office automation workflows.

Details

Author
demo-ai
Downloads
321
Categories
Communication, AI, Productivity, Automation

- Smart Meeting Summary — Automatically generates concise meeting summaries.
- Action Item Tracking — Extracts TODOs, owners, and deadlines from conversations.
- AI Knowledge Base — Archives historical meeting records into searchable knowledge assets.
- Multi‑language Support — Supports Chinese and English collaborative meetings.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Meeting Notes Ai Mcp
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

The server exposes four tools: summarize_meeting for AI meeting summaries, extract_todos for extracting action items, classify_topics for topic classification, and export_markdown for exporting markdown reports. Configure and invoke these tools via an MCP-compatible client.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "meeting notes ai mcp": {
            "meeting-notes-ai": {
                "command": "docker",
                "args": [
                    "run",
                    "--rm",
                    "-p",
                    "8080:8080",
                    "-e",
                    "OPENAI_API_KEY",
                    "-e",
                    "MCP_ENV=production",
                    "demo/meeting-notes-mcp:latest"
                ],
                "env": {
                    "OPENAI_API_KEY": "sk-demo-key",
                    "MCP_ENV": "production"
                }
            }
        }
    }
}

McpServers

{
    "meeting-notes-ai": {
        "command": "docker",
        "args": [
            "run",
            "--rm",
            "-p",
            "8080:8080",
            "-e",
            "OPENAI_API_KEY",
            "-e",
            "MCP_ENV=production",
            "demo/meeting-notes-mcp:latest"
        ],
        "env": {
            "OPENAI_API_KEY": "sk-demo-key",
            "MCP_ENV": "production"
        }
    }
}

Meeting Notes AI MCP

Overview

Meeting Notes AI MCP is an enterprise-grade AI meeting assistant server based on the Model Context Protocol (MCP). It provides: - Real-time meeting summarization - Action item extraction - Multi-speaker transcript organization - Office workflow automation - AI knowledge archiving ---

Features

Smart Meeting Summary

Automatically generate concise meeting summaries.

Action Item Tracking

Extract TODOs, owners, and deadlines from conversations.

AI Knowledge Base

Archive historical meeting records into searchable knowledge assets.

Multi-language Support

Supports Chinese and English collaborative meetings. ---

Example Use Cases

- Product requirement review - Technical architecture discussion - Daily stand-up meetings - Client communication records - Project milestone synchronization ---

Supported Tools

| Tool | Description | |------|-------------| | summarize_meeting | Generate AI meeting summary | | extract_todos | Extract action items | | classify_topics | Topic classification | | export_markdown | Export markdown report | ---

Security

- No sensitive local file access - No arbitrary command execution - Supports enterprise permission isolation - API token authentication enabled ---

License

MIT License
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.