Connect
Optimize
Secure
Live 16 Actions
Fireflies.ai MCP Server
for AI Agents
StackOne's Fireflies.ai MCP server gives AI agents ready-to-use actions for Fireflies.ai — with built-in authentication, security, governance, token efficiency, and high tool-calling accuracy.
Fireflies.ai MCP Server
Built by 
StackOne
StackOne 
Coverage
16 Agent Actions
Create, read, update, and delete across Fireflies.ai — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Fireflies.ai MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Fireflies.ai tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Fireflies.ai call.
Tools Discovery →What is the Fireflies.ai MCP Server?
A Fireflies.ai MCP server lets AI agents read and write Fireflies.ai data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Fireflies.ai MCP server ships with pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Fireflies.ai MCP Tools and Actions
Every action from Fireflies.ai's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Analytics
- Get Analytics
Retrieve team and per-user analytics including conversation metrics (filler words, questions, sentiments, talk/listen ratio, words per minute) and meeting statistics (count, duration). Optional start_time and end_time filter the period (ISO 8601). Note: analytics data may not be available on all Fireflies plans.
Meeting Analytics
- Get Meeting Analytics
Retrieve per-meeting analytics for a specific transcript including sentiment percentages, content categories (questions, date/times, metrics, tasks), and per-speaker statistics. Use list_transcripts first to obtain the transcript_id. For team-wide analytics use get_analytics instead.
Meeting Sentiments
- Get Meeting Sentiments
Retrieve sentiment percentages (negative, neutral, positive) for a specific meeting transcript. Use list_transcripts first to obtain the transcript_id. For full analytics including speaker stats use get_meeting_analytics instead.
Channels
- List Channels
Retrieve a list of channels by querying transcripts that have channel assignments. Channels are created in the Fireflies web UI and can be used to organize transcripts.
Contacts
- List Contacts
Retrieve a list of contacts from meetings (people who have participated in meetings)
Soundbites
- Create Soundbite
Create a soundbite (clip) from a transcript by specifying start and end timestamps
- Get Soundbite
Retrieve detailed information about a specific soundbite including captions and sources
- List Soundbites
Retrieve a list of soundbites. IMPORTANT - At least one filter is required, set variables.mine=true to get your soundbites, or variables.transcript_id to filter by transcript, or variables.my_team=true for team soundbites.
Transcripts
- List Transcripts
Retrieve a list of transcripts with optional filtering by date range, keyword search, or host email. Returns transcript metadata including IDs. Use get_transcript with the returned ID to retrieve full conversation text and summary.
- Get Transcript
Retrieve detailed information about a specific transcript including full conversation text and summary. Use list_transcripts first to obtain the transcript ID.
Transcript Privacys
- Set Transcript Privacy
Update the privacy setting of a transcript. Valid privacy values are link, owner, participants, teammatesandparticipants, or teammates. Use list_transcripts first to obtain the transcript_id.
Transcript Channels
- Update Transcript Channel
Update the channel assignment for a transcript (moves transcript to specified channel). Use list_transcripts to get transcript_id and list_channels to get channel_id.
Meeting Summarys
- Get Meeting Summary
Get the AI-generated summary for a specific meeting. Use list_transcripts first to obtain the transcriptId.
Meetings
- Search Meetings
Search meeting transcripts by keyword with optional filters.
Users
- Get User
Retrieve information about a specific user by ID, or the current API key owner if no ID is provided. Use list_users to obtain user IDs.
- List Users
Retrieve a list of all users within your team
Set Up Your Fireflies.ai MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Fireflies.ai in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More AI & ML MCP Servers
Fireflies.ai MCP Server Resources
Automating Meeting Sharing with a Custom Fireflies MCP Server
StackOne's Fireflies MCP connector adds write operations the Fireflies MCP server lacks. Automate meeting sharing with Claude Code.
8 min
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Fireflies.ai MCP Server FAQ
Fireflies.ai MCP server vs direct API integration — what's the difference?
A Fireflies.ai MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Fireflies.ai. A Fireflies.ai MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Fireflies.ai at runtime. StackOne provides both.
How does Fireflies.ai authentication work for AI agents?
Fireflies.ai authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Fireflies.ai account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Fireflies.ai MCP tools vulnerable to prompt injection?
Yes — Fireflies.ai MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Fireflies.ai agent and how do I avoid it?
Context bloat happens when Fireflies.ai tool schemas and API responses eat your Fireflies.ai agent's memory, preventing it from reasoning effectively. A single Fireflies.ai query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Fireflies.ai agent can access?
Yes — you can limit which actions your Fireflies.ai agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Fireflies.ai MCP server?
Yes — you can create custom agent actions for your Fireflies.ai MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Fireflies.ai's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Fireflies.ai MCP server?
Skip a Fireflies.ai MCP server if your integration is purely software-to-software — direct Fireflies.ai API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Fireflies.ai actions at runtime.
What AI frameworks and AI clients does the StackOne Fireflies.ai MCP server support?
The StackOne Fireflies.ai MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.