How to Use the Fireflies.ai MCP in OpenAI Agents SDK

Q: How do I connect Fireflies.ai to my OpenAI Agents SDK project?

Install the SDK, then initialize the MCPServerStreamableHttp client pointing to your Vinkius endpoint. Pass this server instance in the mcpservers list when creating your Agent. The SDK automatically registers all 12 tools, including listtranscripts and gettranscript.

Q: Can an agent join an ongoing Zoom call using Fireflies.ai and OpenAI Agents SDK?

Yes, your agent can call addtolivemeeting to invite the recorder bot to any active call URL. The OpenAI Agents SDK handles this action using its built-in guardrails to verify the meeting link before execution.

Q: Can I query AskFred threads directly from OpenAI Agents SDK using Fireflies.ai?

You can. Use listaskfredthreads to find existing discussions or createaskfredthread to start a new inquiry. The agent receives the response directly within its execution loop, allowing it to make decisions based on past meeting summaries.

Q: How does tool caching work with this MCP integration?

You should set cacheToolsList=True in your server parameters. This prevents the agent from making redundant network requests to discover tools like getanalytics or listusers on every turn, keeping latency low.

Feed live meeting data and transcripts directly to your OpenAI Agents SDK pipelines with zero-config tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect Fireflies.ai to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live call transcripts to OpenAI agents

Stop copying and pasting meeting notes into your prompt templates. This MCP Server lets your OpenAI Agents SDK setup pull raw conversation text directly from your calls. By executing `get_transcript` or listing recent files with `list_transcripts`, your agents inspect what was actually said without human intervention. You can deploy specialized OpenAI Agents SDK runs that watch for specific verbal cues in your Fireflies.ai transcripts. The agent automatically triggers when a new Fireflies.ai transcript is ready, letting OpenAI Agents SDK parse the text for action items.

Automate live meeting tracking

Keep your OpenAI Agents SDK agents plugged into active Fireflies.ai conversations. Use `add_to_live_meeting` to send the Fireflies bot to your scheduled calendar events on the fly, or use `list_active_meetings` to see what is currently recording. If a meeting topic shifts, your OpenAI Agents SDK agent can use `update_meeting_title` to keep your records organized. This lets you build autonomous OpenAI Agents SDK agents that manage their own context gathering during live Fireflies.ai standups.

Run deep meeting analysis on OpenAI Agents SDK runs

Sometimes your OpenAI Agents SDK workflows need more than raw text from Fireflies.ai. This MCP Server lets your OpenAI Agents SDK agents run `get_analytics` to extract speaker talk-time, sentiment, and silence metrics. Your OpenAI Agents SDK pipeline can use these data points to flag unproductive syncs or track team engagement. If you need to drill down into specific topics, your OpenAI Agents SDK agent can spawn a thread using `create_ask_fred_thread` or pull existing messages with `get_ask_fred_thread`. This gives your OpenAI Agents SDK workflows direct access to the AskFred analysis engine.

Setup guide

Set up Fireflies.ai MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Fireflies.ai tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Fireflies.ai tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fireflies.ai tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Fireflies.ai Agent",
            instructions="You have access to Fireflies.ai tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK, then initialize the `MCPServerStreamableHttp` client pointing to your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when creating your Agent. The SDK automatically registers all 12 tools, including `list_transcripts` and `get_transcript`.

Yes, your agent can call `add_to_live_meeting` to invite the recorder bot to any active call URL. The OpenAI Agents SDK handles this action using its built-in guardrails to verify the meeting link before execution.

You can. Use `list_ask_fred_threads` to find existing discussions or `create_ask_fred_thread` to start a new inquiry. The agent receives the response directly within its execution loop, allowing it to make decisions based on past meeting summaries.

You should set `cacheToolsList=True` in your server parameters. This prevents the agent from making redundant network requests to discover tools like `get_analytics` or `list_users` on every turn, keeping latency low.

Your sensitive meeting transcripts and audio data never sit on external servers. Vinkius runs the server in an ephemeral sandbox, passing requests directly to the Fireflies API. You control access via your endpoint token, ensuring only authorized agents can call `get_transcript`.

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