Fellow MCP Server
Provides access to Fellow.ai meeting data including transcripts, summaries, action items, and participants, with local SQLite caching for fast searches and offline access.
README
Fellow MCP Server
A local MCP (Model Context Protocol) server that wraps the Fellow.ai API, providing tools to access meeting data, transcripts, summaries, action items, and participants.
Features:
- Local SQLite database for caching meeting data
- Automatic incremental sync to keep action items fresh
- Full-text search across cached notes
- Find meetings by participant
Installation
npm install -g fellow-mcp
Setup
1. Get your Fellow API credentials
- Log into your Fellow account
- Navigate to Developer API settings in your User settings
- Generate a new API key
- Note your workspace subdomain (the part before
.fellow.appin your URL)
2. Configure your MCP client
Add the following to your MCP client configuration (e.g., ~/.config/opencode/opencode.json):
{
"mcp": {
"fellow": {
"type": "local",
"command": ["npx", "-y", "fellow-mcp"],
"environment": {
"FELLOW_API_KEY": "YOUR_FELLOW_API_KEY_HERE",
"FELLOW_SUBDOMAIN": "YOUR_SUBDOMAIN"
},
"enabled": true
}
}
}
Available Tools
API Tools (Direct Fellow API calls)
search_meetings
Search for meetings/recordings in Fellow.
Parameters:
title(optional): Filter by meeting title (case-insensitive partial match)created_at_start(optional): Filter meetings created after this date (ISO format)created_at_end(optional): Filter meetings created before this date (ISO format)limit(optional): Maximum number of results (1-50, default 20)
get_meeting_transcript
Get the full transcript of a meeting recording with speaker labels and timestamps.
Parameters:
recording_id(optional): The ID of the recordingmeeting_title(optional): Search by meeting title
get_meeting_summary
Get the meeting summary/notes content including agenda items, discussion topics, and decisions.
Parameters:
note_id(optional): The ID of the noterecording_id(optional): Get the summary for a recording's associated notemeeting_title(optional): Search by meeting title
get_action_items
Extract action items from a single meeting's notes.
Parameters:
note_id(optional): The ID of the notemeeting_title(optional): Search by meeting title
get_meeting_participants
Get the list of participants/attendees for a meeting.
Parameters:
note_id(optional): The ID of the notemeeting_title(optional): Search by meeting title
Database Tools (Local SQLite cache)
sync_meetings
Sync meetings from Fellow API to local database.
Parameters:
force(optional, default: false): If true, performs full re-sync. Otherwise does incremental sync (only new/updated since last sync)include_transcripts(optional, default: false): If true, also fetches and stores transcripts (slower)
get_all_action_items
Get all action items from the local database. Automatically performs incremental sync first to ensure data is fresh.
Parameters:
assignee(optional): Filter by assignee name (partial match)show_completed(optional, default: false): If true, includes completed action itemssince(optional): Only return action items from meetings on or after this date (ISO format: YYYY-MM-DD)
get_meetings_by_participants
Find meetings that included specific participants.
Parameters:
emails(required): List of email addresses to search forrequire_all(optional, default: false): If true, only return meetings where ALL specified participants attended
search_cached_notes
Full-text search across all cached meeting notes (titles and content).
Parameters:
query(required): Search query
get_sync_status
Get the current sync status and database statistics.
Local Database
Meeting data is cached in a local SQLite database at ~/.fellow-mcp/fellow.db. This enables:
- Fast local searches
- Querying across all action items
- Finding meetings by participant
- Offline access to cached data
The database stores:
- Notes (meeting summaries, agendas, content)
- Recordings (with optional transcripts)
- Action items (parsed from notes with assignee/due date extraction)
- Participants (email addresses)
Environment Variables
| Variable | Required | Description |
|---|---|---|
FELLOW_API_KEY |
Yes | Your Fellow API key |
FELLOW_SUBDOMAIN |
Yes | Your Fellow workspace subdomain |
Development
# Watch mode for development
npm run dev
# Build
npm run build
# Test API connection
node --env-file=.env test-api.js
Requirements
- Node.js >= 18.0.0
- A Fellow.ai account with API access
License
MIT
API Reference
This MCP server wraps the Fellow Developer API. The API uses:
X-API-KEYheader for authentication- POST requests for list operations (with JSON body for filters/pagination)
- GET requests for retrieving individual resources
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。