How to Use the AssemblyAI MCP in Windsurf

Q: How do I configure the AssemblyAI MCP Server in Windsurf?

Open /.codeium/windsurf/mcpconfig.json and add the server configuration under the mcpServers key. You can also do this directly in the Windsurf UI under Settings -> Cascade -> MCP Servers UI. Once you click refresh, Cascade instantly registers all six speech-to-text tools.

Q: Can Windsurf transcribe local video files using AssemblyAI?

No, the transcribeaudio tool requires a publicly accessible URL for your media files. If you have local files, upload them to a temporary bucket first, then let Cascade pass that URL to the server.

Q: How does Windsurf handle long audio polling with AssemblyAI?

Cascade handles this autonomously by calling gettranscript in a loop. It checks the status field and waits before checking again, so you do not have to manually prompt it to retry.

Q: How can I view previous transcription jobs in this IDE?

Ask Cascade to fetch your history. It will trigger listtranscripts to pull your recent runs and display them in your chat panel as a clean list.

Feed raw audio URLs to Windsurf and let Cascade run transcription pipelines down to the sentence level.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to Windsurf

Create your Vinkius account to connect AssemblyAI 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 AssemblyAI with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build transcription pipelines in Windsurf

Cascade takes a raw media link and runs the entire speech-to-text pipeline without you babysitting it. It starts the job with `transcribe_audio` and monitors the progress until it gets a completed status. You do not have to write polling loops because Cascade handles the state machine. Once the file is ready, Cascade pulls the text down with `get_transcript` and formats the output. If you need to map timestamps to specific video frames, the agent automatically maps the response JSON directly into your UI components.

Sentence-level analysis with Cascade

Break down massive audio files without hitches. Cascade uses `get_transcript_sentences` to slice long-form recordings into clean, manageable strings of text. This lets your agent analyze sentiment or extract action items block by block without hitting token limits. For longer conversations, Cascade calls `get_transcript_paragraphs` to preserve the natural flow of the dialogue. It feeds these paragraph chunks directly into your editor, writing clean markdown files for your documentation.

Clean up audio assets on the fly

Keep your storage footprint clean by removing stale speech data from your workspace. This AssemblyAI MCP Server lets Cascade clean up after itself by invoking `delete_transcript` as soon as it finishes parsing the text. You can have Cascade run `list_transcripts` to find old jobs, compare them against your local project files, and purge the remote copies. This keeps your data footprint small and prevents stale transcription runs from cluttering your workspace.

Setup guide

Set up AssemblyAI 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 AssemblyAI 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 AssemblyAI payment history." If connected, Cascade will call the AssemblyAI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "assemblyai-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 AssemblyAI. 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 AssemblyAI 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 AssemblyAI MCP in Windsurf

Open `~/.codeium/windsurf/mcp_config.json` and add the server configuration under the `mcpServers` key. You can also do this directly in the Windsurf UI under Settings -> Cascade -> MCP Servers UI. Once you click refresh, Cascade instantly registers all six speech-to-text tools.

No, the `transcribe_audio` tool requires a publicly accessible URL for your media files. If you have local files, upload them to a temporary bucket first, then let Cascade pass that URL to the server.

Cascade handles this autonomously by calling `get_transcript` in a loop. It checks the status field and waits before checking again, so you do not have to manually prompt it to retry.

Ask Cascade to fetch your history. It will trigger `list_transcripts` to pull your recent runs and display them in your chat panel as a clean list.

No, your raw audio files and transcription texts are processed in an ephemeral Vinkius sandbox. Your media URLs go directly to AssemblyAI for processing, and Windsurf only reads the text output via the secure MCP link.

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