How to Use the Fireflies.ai MCP in Windsurf

Q: How does Windsurf use the Fireflies.ai MCP Server to automate coding tasks?

Cascade uses gettranscript to read your team's live discussions. It then writes code in your workspace based on requirements developers discussed in the call.

Q: Can I ask questions about my team meetings directly inside Windsurf using Fireflies.ai?

Yes. Cascade calls askfred to query specific details across your meetings, feeding the answers directly into your open files.

Q: How do I set up the Fireflies.ai MCP Server connection in Windsurf?

Open your mcpconfig.json file in Windsurf, add the MCP Server details under the mcpServers key, and refresh Cascade's tool panel.

Q: Can Cascade handle audio uploads for transcription?

Yes, Cascade uses uploadaudio to send your local audio recordings to the transcription queue and waits for the job to finish.

Feed your meeting transcripts directly to Windsurf's Cascade agent to build features, write docs, and track team tasks without manual copy-paste.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reconcile tasks from live meeting discussions

The `get_transcript` tool pulls raw text from your recorded calls directly into Windsurf's context window. Cascade reads these transcripts, detects action items, and generates code or updates files in your workspace without you prompting each step. You tell Cascade to update a project roadmap based on the last standup. It calls `list_transcripts` to find the correct session, pulls the text, and writes the markdown changes directly to your repository.

Build internal tools using meeting outputs

The `get_ai_app_outputs` tool exposes structured summaries and custom tracker data directly to your Windsurf workspace. Cascade uses this structured JSON to build internal dashboards, populate local databases, or write test suites matching actual user feedback from calls. Instead of manually inspecting meeting notes, you let the agent write a script to parse these outputs. It writes, tests, and runs the script in your terminal, handling the entire pipeline autonomously.

Chain live meeting actions with this MCP Server

The `add_to_live_meeting` tool lets your Windsurf agent invite the Fireflies bot to active video calls with a single command. Cascade handles the live integration, tracks the status, and prepares your workspace for the incoming transcript. When the call ends, Cascade detects the new data, uses `ask_fred` to extract technical requirements discussed during the call, and instantly drafts the corresponding code branches.

Setup guide

Set up Fireflies.ai MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Fireflies.ai MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Fireflies.ai payment history." If connected, Cascade will call the Fireflies.ai tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "firefliesai-alternative-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Cascade uses `get_transcript` to read your team's live discussions. It then writes code in your workspace based on requirements developers discussed in the call.

Yes. Cascade calls `ask_fred` to query specific details across your meetings, feeding the answers directly into your open files.

Open your `mcp_config.json` file in Windsurf, add the MCP Server details under the `mcpServers` key, and refresh Cascade's tool panel.

Yes, Cascade uses `upload_audio` to send your local audio recordings to the transcription queue and waits for the job to finish.

Your audio files and transcripts are processed inside a zero-trust sandbox. Windsurf uses temporary tokens that expire immediately after Cascade finishes its run.

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