How to Use the Fireflies.ai MCP in CrewAI

Q: How do multiple CrewAI agents collaborate on Fireflies.ai transcripts?

One agent uses listtranscripts to find the target meeting ID. It passes this ID to a second agent, which calls getaiappoutputs to extract structured action items for the team.

Q: Can a CrewAI agent ask questions about a meeting using Fireflies.ai?

Yes, agents can invoke askfred to query specific details. This allows an autonomous agent to resolve factual disputes by searching the meeting record directly.

Q: How do I limit which Fireflies.ai tools my CrewAI agents can access?

Use the toolfilter option in your MCP Server configuration to expose only safe tools like gettranscript while hiding destructive tools like deletetranscript.

Q: Can I automate live meeting recording using CrewAI and Fireflies.ai?

Yes, configure a scheduling agent to call addtolivemeeting whenever a calendar event starts. The agent handles the bot invite, ensuring every discussion is captured.

Run autonomous agent crews to analyze meetings and coordinate team actions with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fireflies.ai MCP to CrewAI

Create your Vinkius account to connect Fireflies.ai to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Fireflies.ai with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy a multi-agent team to parse meetings

`list_transcripts` feeds raw meeting lists to your research agent, which identifies the highest priority discussions from the past week. A separate analyst agent then takes over to pull specific details using the MCP Server. Using the CrewAI hierarchical process, the analyst agent calls `get_transcript` to extract raw text blocks. The agents collaborate in memory, passing findings back and forth to build a unified report.

Run real-time meeting operations via CrewAI agents

`add_to_live_meeting` lets your coordinator agent dispatch a recording bot to an active call. While the bot records, other agents in the crew stand by to process the output the moment the call ends. This MCP Server tool integrates directly into CrewAI's tool list, allowing agents to decide autonomously when to join a call based on calendar triggers.

Extract and distribute soundbites automatically

`list_soundbites` allows a specialized curator agent to find key audio highlights from your team's calls. The agent matches these snippets with specific agenda items to verify team alignment. If a meeting title is messy, the moderator agent uses `update_meeting_title` to clean up the records. This keeps your entire meeting archive organized without human cleanup.

Setup guide

Set up Fireflies.ai MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Fireflies.ai tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Fireflies.ai Analyst",
    goal="Access and analyze Fireflies.ai data via MCP.",
    backstory="Expert analyst with direct Fireflies.ai access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Fireflies.ai transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Fireflies.ai Analyst",
        goal="Access and analyze Fireflies.ai data via MCP.",
        backstory="Expert analyst with direct Fireflies.ai access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Fireflies.ai transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fireflies.ai. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Fireflies.ai now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Fireflies.ai MCP in CrewAI

One agent uses `list_transcripts` to find the target meeting ID. It passes this ID to a second agent, which calls `get_ai_app_outputs` to extract structured action items for the team.

Yes, agents can invoke `ask_fred` to query specific details. This allows an autonomous agent to resolve factual disputes by searching the meeting record directly.

Use the tool_filter option in your MCP Server configuration to expose only safe tools like `get_transcript` while hiding destructive tools like `delete_transcript`.

Yes, configure a scheduling agent to call `add_to_live_meeting` whenever a calendar event starts. The agent handles the bot invite, ensuring every discussion is captured.

All API communication is encrypted, and the MCP Server executes in an isolated environment. Your meeting transcripts and user list data are never exposed to public LLM training sets.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript