How to Use the Fireflies.ai MCP in AutoGen

Q: How do I register the Fireflies.ai MCP Server tools in AutoGen?

Use the mcpservertools adapter from autogen-extmcp to load the tools. Pass this tool list to your AutoGen AssistantAgent to let your team debate transcript data. This setup allows agents to coordinate meeting tasks autonomously.

Q: Can AutoGen agents delete transcripts using the Fireflies.ai MCP integration?

Yes, if authorized, an AutoGen agent can call deletetranscript if the team agrees a meeting transcript contains highly sensitive data that must be purged immediately.

Q: How do AutoGen agents use Fireflies.ai to handle team directories?

Agents use listusers and getuser to identify team members mentioned in transcripts. This allows the AutoGen agents to assign action items to the correct real-world owners after a meeting.

Q: How is user account data secured during AutoGen operations?

User details accessed via getuser are protected by single-token authentication. This MCP server secures your user details within isolated V8 runtimes, meaning AutoGen agents cannot leak sensitive team directories to unauthorized endpoints.

Build AutoGen agent teams that debate Fireflies.ai meeting analytics, manage active recordings, and query AskFred threads to reach decisions.

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 AutoGen

Create your Vinkius account to connect Fireflies.ai to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Meeting Performance with AutoGen Teams

The `get_analytics` tool feeds raw talk-time and sentiment metrics into a multi-agent debate. A performance agent and a product agent analyze the metrics to negotiate team focus areas. By forcing agents to argue over the data, you get balanced operational insights. The process runs autonomously, ending only when the agents reach a consensus on the next steps.

Control Fireflies.ai MCP Server Actions with AutoGen

Use `add_to_live_meeting` to let your coordination agent invite the recorder to calendar events. Before doing so, a security agent can audit the meeting title using `list_active_meetings` to ensure no sensitive topics are recorded. If the title is vague, the agent uses `update_meeting_title` to clean up the records before saving. This multi-agent check prevents recording errors and keeps your dashboard clean.

Resolve Complex Transcribing Questions in Threads

The `create_ask_fred_thread` tool lets your agent team post complex questions directly to AskFred. One agent drafts the query, another reviews it for clarity, and a third executes the tool call to get the answer. Once the thread is active, the team uses `get_ask_fred_thread` to analyze the response. This collaborative approach ensures that the questions asked are highly targeted, saving API credits.

Setup guide

Set up Fireflies.ai MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Fireflies.ai tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Fireflies.ai_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Fireflies.ai data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Fireflies.ai_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Fireflies.ai data")
    print(result.messages[-1].content)

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 AutoGen

Use the `mcp_server_tools` adapter from `autogen-ext[mcp]` to load the tools. Pass this tool list to your AutoGen `AssistantAgent` to let your team debate transcript data. This setup allows agents to coordinate meeting tasks autonomously.

Yes, if authorized, an AutoGen agent can call `delete_transcript` if the team agrees a meeting transcript contains highly sensitive data that must be purged immediately.

Agents use `list_users` and `get_user` to identify team members mentioned in transcripts. This allows the AutoGen agents to assign action items to the correct real-world owners after a meeting.

Yes. AutoGen's MCP adapter handles schema conversion and streaming over HTTP transports. This keeps agent conversations responsive when fetching large transcripts via `get_transcript`.

User details accessed via `get_user` are protected by single-token authentication. This MCP server secures your user details within isolated V8 runtimes, meaning AutoGen agents cannot leak sensitive team directories to unauthorized endpoints.

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