Convo
Access your meetings, transcripts, summaries, and action items from Convo, an AI meeting assistant. Cross-meeting intelligence: prepare for calls with past context, get weekly digests, and track action items across all meetings. Works before, during, and after your meetings.
README
Convo MCP Server
Access your Convo meetings from any large language model (LLM) that supports MCP (Claude, ChatGPT, Cursor, and more). Meeting intelligence that helps you prepare, follow up, and stay on top of everything.
What you can do
Single meeting:
- Read transcripts with speaker names and timestamps
- Get summaries with key points, decisions, and action items
- Get coaching feedback with communication scores
- Ask any question about a meeting
- Draft follow-up emails that reference actual discussion points
Across meetings:
- Prepare for an upcoming meeting by reviewing all past interactions with a person or company
- Get a weekly digest of all meetings, decisions, and action items
- Find all open action items across your meetings, filtered by owner or priority
Built-in workflows:
- Meeting Prep prompt: one-click briefing before any call
- Weekly Review prompt: consolidated week summary
- Follow-up Blitz prompt: draft follow-up emails for all recent meetings at once
Setup
1. Get your API key
Download the Convo app, open the dashboard, and go to Settings to create an API key. You need a Starter plan or above.
2. Install
npm install -g @itsconvo/mcp-server
3. Configure your AI assistant
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"convo": {
"command": "convo-mcp",
"env": {
"CONVO_API_KEY": "convo_your_api_key_here"
}
}
}
}
Claude Code
claude mcp add convo convo-mcp -e CONVO_API_KEY=convo_your_api_key_here
Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"convo": {
"command": "convo-mcp",
"env": {
"CONVO_API_KEY": "convo_your_api_key_here"
}
}
}
}
Tools
Core
| Tool | Description |
|---|---|
list_meetings |
List and search your meetings |
get_transcript |
Get full meeting transcript |
get_summary |
Get key points, decisions, action items |
get_feedback |
Get coaching feedback and scores |
ask_about_meeting |
Ask any question about a meeting |
draft_followup_email |
Generate a follow-up email |
share_meeting |
Create a shareable meeting link |
get_upcoming_meetings |
View upcoming calendar events |
get_account_info |
Check your plan and API usage |
Cross-Meeting Intelligence
| Tool | Description |
|---|---|
prepare_for_meeting |
Get a briefing from all past meetings with a person or company |
weekly_digest |
Consolidated digest of all meetings over a time period |
find_action_items |
Find all action items across meetings, filter by owner |
Prompts
| Prompt | Description |
|---|---|
meeting-prep |
Pre-built workflow to prepare for a meeting |
weekly-review |
Pre-built workflow for your weekly meeting review |
follow-up-blitz |
Draft follow-up emails for all recent meetings |
Example prompts
- "Prepare me for my meeting with Sarah tomorrow"
- "What action items am I behind on?"
- "Give me a digest of all my meetings this week"
- "Draft follow-up emails for all my calls from the last 3 days"
- "What have we discussed with Acme Corp over the last month?"
- "How was my communication in today's client call?"
- "What did we decide about pricing across all recent meetings?"
Requirements
- Convo account with Starter plan or above
- API key from your Convo app (Settings > API Keys)
- Node.js 18+
Links
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。