How to Use the Abridge (AI Clinical Documentation API) MCP in Claude Code

Q: How do I configure the Abridge (AI Clinical Documentation API) in Claude Code?

Run the command claude mcp add --transport http abridge-mcp -- Vinkius-URL in your terminal. This command updates your /.claude.json configuration file. Claude Code immediately discovers the clinical tools for your next session.

Q: How does Claude Code verify that my Abridge (AI Clinical Documentation API) notes are ready?

The agent uses getrecordingstatus to poll the API. Once the tool returns a completed status, Claude Code automatically calls getclinicalnotes to fetch the structured medical documentation.

Q: Can I redirect the output of the clinical notes tool to a local database?

Yes, Claude Code can parse the JSON returned by getclinicalnotes and format it as SQL inserts or CSV rows. You can then pipe that output directly to your local database client.

Pipe raw clinical audio and structured medical notes directly through Claude Code using the command line.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Abridge (AI Clinical Documentation API) MCP to Claude Code

Create your Vinkius account to connect Abridge (AI Clinical Documentation API) 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 Abridge (AI Clinical Documentation API) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger medical audio uploads from your terminal

The `create_recording` tool lets you upload raw patient audio files or start new recording sessions directly from your shell. Claude Code invokes this tool to send local audio files to the Abridge API. This means you can pipe local audio directories straight into the clinical API. Your terminal agent handles the file paths and initiates the processing tasks without any manual browser uploads.

Monitor processing queues with headless commands

The `get_recording_status` tool retrieves the real-time status of your clinical audio processing tasks. Claude Code polls this tool to track whether a recording is pending, processing, completed, or failed. You can run this in continuous integration scripts or cron jobs to process batches of medical audio. The terminal agent monitors the queue and triggers downstream scripts the moment the status changes to completed.

Export structured clinical notes via this MCP Server

The `get_clinical_notes` tool extracts structured medical text, including history of present illness, physical exam, and assessment plans. Claude Code runs this tool to fetch the structured JSON directly into your terminal. This MCP Server allows you to pipe clinical notes directly into other CLI tools or local databases. You can format the output as JSON, markdown, or raw text and redirect it to your electronic health record systems.

Setup guide

Set up Abridge (AI Clinical Documentation API) 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 abridge-ai-clinical-documentation-api-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Abridge (AI Clinical Documentation API) transactions." It will automatically discover and invoke the available Abridge (AI Clinical Documentation API) tools.

Terminal

claude mcp add --transport http abridge-ai-clinical-documentation-api-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 Abridge (AI Clinical Documentation API) 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": {
    "abridge-ai-clinical-documentation-api-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 Abridge. 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 Abridge (AI Clinical Documentation API) 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 Abridge (AI Clinical Documentation API) MCP in Claude Code

Run the command `claude mcp add --transport http abridge-mcp -- [Vinkius-URL]` in your terminal. This command updates your `~/.claude.json` configuration file. Claude Code immediately discovers the clinical tools for your next session.

Yes, you can instruct Claude Code to loop through a folder of audio files. The agent will call `create_recording` for each file and track their progress in parallel.

The agent uses `get_recording_status` to poll the API. Once the tool returns a completed status, Claude Code automatically calls `get_clinical_notes` to fetch the structured medical documentation.

Yes, Claude Code can parse the JSON returned by `get_clinical_notes` and format it as SQL inserts or CSV rows. You can then pipe that output directly to your local database client.

All audio files and clinical notes transit through Vinkius's zero-trust gateway. Your terminal session communicates over encrypted HTTPS channels, and the V8 sandbox prevents data persistence. No patient data is cached on your local machine or exposed in raw logs.

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