About Fireflies MCP Server
Fireflies MCP Server connects MCP clients to the Fireflies.ai API for meeting transcript retrieval, search, detail lookup, and summary generation. It is suited to workflows that need to find or review meeting records.
Key features
- 01List transcripts with date filters
- 02Retrieve transcript details and speakers
- 03Search transcripts by keywords
- 04Generate bullet-point or paragraph summaries
Use cases
- 01Find transcripts from a date range
- 02Review transcript content and speaker details
- 03Summarize a meeting transcript
MCP support
The MCP server exposes tools to retrieve and filter transcripts, inspect transcript details, search by keywords, and generate summaries through the Fireflies.ai API.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEFireflies MCP Server
MCP Server for the Fireflies.ai API, enabling transcript retrieval, search, and summary generation.
Features
- Transcript Management: Retrieve and search meeting transcripts with filtering options
- Detailed Information: Get comprehensive details about specific transcripts
- Advanced Search: Find transcripts containing specific keywords or phrases
- Summary Generation: Generate concise summaries of meeting transcripts in different formats
Tools
-
fireflies_get_transcripts- Retrieve a list of meeting transcripts with optional filtering
- Inputs:
limit(optional number): Maximum number of transcripts to returnfrom_date(optional string): Start date in ISO format (YYYY-MM-DD)to_date(optional string): End date in ISO format (YYYY-MM-DD)
- Returns: Array of transcript objects with basic information
-
fireflies_get_transcript_details- Get detailed information about a specific transcript
- Inputs:
transcript_id(string): ID of the transcript to retrieve
- Returns: Comprehensive transcript details including speakers, content, and metadata
-
fireflies_search_transcripts- Search for transcripts containing specific keywords
- Inputs:
query(string): Search query to find relevant transcriptslimit(optional number): Maximum number of transcripts to return
- Returns: Array of matching transcript objects
-
fireflies_generate_summary- Generate a summary of a meeting transcript
- Inputs:
transcript_id(string): ID of the transcript to summarizeformat(optional string): Format of the summary ('bullet_points' or 'paragraph')
- Returns: Generated summary text
Setup
Fireflies API Key
Create a Fireflies API Key with appropriate permissions:
- Go to the Fireflies.ai dashboard
- Navigate to Settings > API
- Generate a new API key
- Copy the generated key
Usage with Claude Desktop
To use this with Claude Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"fireflies": {
"command": "npx",
"args": [
"-y",
"@props-labs/mcp/fireflies"
],
"env": {
"FIREFLIES_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
Installation
- Clone this repository
- Install dependencies:
npm install
# or
pnpm install
- Build the project:
npm run build
# or
pnpm build
Usage
Starting the Server
FIREFLIES_API_KEY=your_api_key npm start
# or
FIREFLIES_API_KEY=your_api_key pnpm start
You can also use the setup script:
./setup.sh
FIREFLIES_API_KEY=your_api_key npm start
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Comments
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.