How to Use the AssemblyAI MCP in Claude Code

Q: How do I add the AssemblyAI MCP Server to Claude Code?

Run claude mcp add --transport http assemblyai -- in your terminal. This adds the server configuration directly to your /.claude.json file, exposing all six audio tools to your MCP client.

Q: Can I pipe audio files directly into Claude Code for AssemblyAI processing?

No, the transcribeaudio tool requires a URL. You should upload your audio file to a public bucket or temporary hosting first, then pass that URL to Claude Code to start the run.

Q: How does Claude Code handle large AssemblyAI transcription queues?

Your terminal agent runs listtranscripts to check active jobs. It can loop through the queue, calling gettranscript for each ID and writing the outputs to your local disk sequentially.

Pipe AssemblyAI transcription outputs directly into terminal scripts and CI/CD pipelines with Claude Code.

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 Claude Code

Create your Vinkius account to connect AssemblyAI to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless speech-to-text pipelines in Claude Code

Run your transcription workflows straight from the command line. Claude Code uses `transcribe_audio` to kick off speech-to-text runs directly from raw media URLs. You do not need a browser or an IDE to manage your audio assets. The tool feeds progress updates straight to your terminal. Once the job is done, Claude Code calls `get_transcript` and pipes the resulting text directly into other CLI utilities or saves it as a local file.

Terminal-driven text segmentation

Slice up massive audio files for automated terminal processing. Claude Code triggers `get_transcript_sentences` to extract timed sentence blocks, making it easy to grep for specific keywords or timestamps in your shell. For clean documentation, Claude Code calls `get_transcript_paragraphs` to format long-form audio into readable blocks. It dumps this structured text directly to stdout, letting you redirect the output into your static site generator.

Scripted transcription history management

Manage your remote transcription records via terminal commands. This MCP Server lets Claude Code run `list_transcripts` to audit your active jobs and print a clean list of IDs directly to your console. When you need to purge data for compliance, Claude Code calls `delete_transcript` to wipe the records. You can script this into your deployment pipelines to ensure no audio data lingers after a build completes.

Setup guide

Set up AssemblyAI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see assemblyai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest AssemblyAI transactions." It will automatically discover and invoke the available AssemblyAI tools.

Terminal

claude mcp add --transport http assemblyai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "assemblyai-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http assemblyai -- ` in your terminal. This adds the server configuration directly to your `~/.claude.json` file, exposing all six audio tools to your MCP client.

No, the `transcribe_audio` tool requires a URL. You should upload your audio file to a public bucket or temporary hosting first, then pass that URL to Claude Code to start the run.

Your terminal agent runs `list_transcripts` to check active jobs. It can loop through the queue, calling `get_transcript` for each ID and writing the outputs to your local disk sequentially.

Yes, Claude Code can execute these tools inside non-interactive environments like GitHub Actions. It will initiate the transcription, wait for completion, and commit the parsed text directly to your repo.

Your audio URLs and text transcripts are processed inside an isolated V8 sandbox on Vinkius. The CLI agent communicates over a secure, single-token MCP endpoint, meaning your transcription records never touch unauthenticated networks.

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