How to Use the AssemblyAI MCP in Cursor

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

Create a .cursor/mcp.json file in your project root or add it to your global settings. Define the server under the mcpServers block with the required URL or command. Once configured, enable Agent mode in the chat to start using the audio tools.

Q: Can Cursor automatically summarize audio using AssemblyAI?

Yes, your agent can call getsummary on any completed transcript ID. This lets the editor summarize long audio files and insert the markdown summary directly into your project files.

Q: Does the AssemblyAI toolset in Cursor support local file paths?

No, the transcribeaudiourl tool requires a web-accessible URL to start processing. If you have local files, you must upload them to a cloud storage bucket or temporary hosting before passing the link to the editor.

Q: Can I track transcription progress inside Cursor?

Yes, the agent uses gettranscript to check the status of your queue. It will poll the API and let you know when the text is ready so you don't have to manually check the dashboard.

Generate code that acts on live transcription data directly in Cursor using Agent mode.

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 Cursor

Create your Vinkius account to connect AssemblyAI to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch live transcripts directly into your Cursor editor

The `get_transcript` tool pulls the exact text of your audio files directly into your active workspace. When writing audio processing apps, your agent uses `list_transcripts` to pull real API payloads instead of static mock files. This means you can build and test your media features with actual data. The MCP server ensures your editor has real-time access to the API status without switching to an external terminal.

Map speakers and chapters inside the Cursor code editor

The `get_speakers` tool identifies individual voices in an audio file and maps them to their respective dialogue blocks. Your agent can combine this with `get_chapters` to build structured, timed navigation menus for your frontend code. Instead of guessing the JSON structure, the agent calls these tools to see the exact schema returned by the API. This speeds up UI development since your editor knows the exact shape of the incoming data.

Automate sentiment and topic tagging in your codebase

The `get_sentiments` tool analyzes the text to determine the mood of each spoken sentence. Your agent can also call `get_topics` to automatically tag your files with relevant subject matter. If a test run fails or you need to clear out test files, the agent can call `delete_transcript` to keep your workspace clean. This gives you full control over your transcription pipeline directly from the editor.

Setup guide

Set up AssemblyAI MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the AssemblyAI MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent AssemblyAI transactions." If the MCP tools are loaded correctly, Cursor will call the AssemblyAI tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "assemblyai-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 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 Cursor

Create a `.cursor/mcp.json` file in your project root or add it to your global settings. Define the server under the `mcpServers` block with the required URL or command. Once configured, enable Agent mode in the chat to start using the audio tools.

Yes, your agent can call `get_summary` on any completed transcript ID. This lets the editor summarize long audio files and insert the markdown summary directly into your project files.

No, the `transcribe_audio_url` tool requires a web-accessible URL to start processing. If you have local files, you must upload them to a cloud storage bucket or temporary hosting before passing the link to the editor.

Yes, the agent uses `get_transcript` to check the status of your queue. It will poll the API and let you know when the text is ready so you don't have to manually check the dashboard.

Your audio URLs and transcripts are processed through Vinkius's secure, zero-trust sandbox. The editor only transmits the necessary identifiers to fetch your transcription data, and we do not store your media files. You can use `delete_transcript` to immediately remove any sensitive transcription records from the API.

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