Fireflies MCP Server

Fireflies MCP Server

Enables access to Fireflies.ai meeting transcripts with capabilities to retrieve, search, filter, and generate AI-powered summaries of meeting content through the Fireflies API.

Category
访问服务器

README

Fireflies MCP Server

npm version MIT License PRs Welcome

Supercharge your meeting workflows with seamless transcript access, search, and AI-powered summaries—right from your terminal or automation tools!


🚀 Introduction

Fireflies MCP Server is an open source Modern Command Protocol (MCP) server that unlocks the full power of the Fireflies.ai API. Instantly retrieve, search, and summarize your meeting transcripts with simple commands or integrate into your favorite tools. Perfect for productivity enthusiasts, automation fans, and teams who want to get more from their meeting data.


✨ Why Fireflies MCP Server?

  • Instant Access: Fetch and filter all your Fireflies meeting transcripts in seconds.
  • Deep Insights: Get detailed transcript info, including speakers and full content.
  • Smart Search: Find exactly what you need with powerful keyword and phrase search.
  • AI Summaries: Generate concise, actionable summaries in your preferred format.
  • Easy Integration: Works with Claude Desktop, scripts, and any MCP-compatible client.
  • Open Source & Extensible: Community-driven, MIT-licensed, and ready for your contributions!

⚡️ Quick Start

# 1. Install (requires Node.js and npm or pnpm)
npm install -g fireflies-mcp-server

# 2. Get your Fireflies API key from https://fireflies.ai/dashboard/settings/api

# 3. Start the server
FIREFLIES_API_KEY=your_api_key fireflies-mcp-server

🛠 Features

  • Transcript Management: List and filter your Fireflies meeting transcripts
  • Transcript Details: Retrieve in-depth information for any transcript, including speakers and full content
  • Keyword Search: Locate transcripts by searching for specific words or phrases
  • Automated Summaries: Instantly generate concise summaries in either paragraph or bullet point format

🔌 Endpoints

  • fireflies_get_transcripts — List transcripts (with optional filters: limit, from_date, to_date)
  • fireflies_get_transcript_details — Get full details for a transcript (transcript_id)
  • fireflies_search_transcripts — Search transcripts by keyword or phrase (query, optional limit)
  • fireflies_generate_summary — Generate a summary for a transcript (transcript_id, optional format)

🧑‍💻 Setup & Usage

1. Prerequisites

2. Installation

npm install
# or
pnpm install

3. Build

npm run build
# or
pnpm build

4. (Optional) Use a Custom Build Directory

By default, the build output goes to the dist directory. To specify a different build/output directory, set the BUILD_DIR environment variable before building:

BUILD_DIR=custom-dist npm run build

This will output the build to custom-dist instead of dist.

5. Configuration for Claude Desktop

After building, you'll want to point Claude Desktop to your custom build directory. Here's what your terminal output and configuration might look like:

$ echo "Add this to your claude_desktop_config.json mcpServers array:"
Add this to your claude_desktop_config.json mcpServers array:

{
  "mcpServers": {
    "fireflies": {
      "command": "node",
      "args": ["/absolute/path/to/custom-dist/index.js"],
      "env": {
        "FIREFLIES_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Replace /absolute/path/to/custom-dist/index.js with the actual path to your custom build output.

6. Running the Server

FIREFLIES_API_KEY=your_api_key npm start
# or
FIREFLIES_API_KEY=your_api_key pnpm start

Or use the setup script:

./setup.sh
FIREFLIES_API_KEY=your_api_key npm start

🤝 Contributing

We love contributions! Whether it's a bug fix, new feature, or documentation improvement, your help is welcome. Please check out CONTRIBUTING.md for guidelines, or open an issue to start a discussion.


💬 Community & Support


📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选