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

Q: How do I install the Abridge (AI Clinical Documentation API) in Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server configuration under the mcpServers key. Alternatively, use the Settings UI under Cascade to add the server URL. Once you click refresh, Cascade instantly registers the clinical tools.

Q: Can Cascade handle large audio files using this MCP Server?

Yes, Cascade handles the file paths and passes them to the createrecording tool. It monitors the upload progress and handles the file transfer in the background. You don't need to manually chunk the audio.

Q: How does Windsurf track the status of my Abridge (AI Clinical Documentation API) transcription?

Cascade loops the getrecordingstatus tool to check if the state has shifted from pending to completed. It does this autonomously in the background. You get a notification the second the structured text is ready.

Q: What structure does the clinical notes tool return?

The getclinicalnotes tool delivers structured JSON containing distinct fields for HPI, physical exams, and assessment plans. Cascade parses this structure to populate your files. You can direct it to format the output into markdown or custom EHR layouts.

Let Windsurf and Cascade convert raw clinical audio into structured medical notes while you focus on patient care.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-generate medical summaries in Windsurf

The `get_clinical_notes` tool extracts structured medical summaries, history of present illness, physical exams, and assessment plans from your patient encounters. Cascade reads the completed status of an audio upload and immediately triggers this tool to pull the clinical text right into your active workspace. You don't have to copy-paste between browser tabs anymore. Because Cascade chains operations, it grabs the raw output from Abridge and formats it directly into your electronic health record templates without waiting for your manual input.

Chain audio uploads and status checks autonomously

The `create_recording` tool starts a new session or uploads raw patient audio files directly to the Abridge API. Once the upload finishes, Cascade uses `get_recording_status` to monitor the processing queue behind the scenes. Instead of babysitting a progress bar, you tell Cascade to alert you when the processing completes. This MCP Server lets your IDE handle the tedious waiting game while you draft treatment plans or review lab results.

Build medical documentation workflows with this MCP Server

This MCP Server exposes the `create_recording`, `get_recording_status`, and `get_clinical_notes` tools so Cascade can build custom medical documentation pipelines right in your editor. You get direct programmatic access to structured clinical data without writing glue code. Cascade uses the live tools to verify file uploads, track processing states, and fetch finalized notes. It connects your development environment directly to clinical APIs, handling the entire pipeline from raw audio file to structured medical file.

Setup guide

Set up Abridge (AI Clinical Documentation API) 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 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

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 Abridge (AI Clinical Documentation API) payment history." If connected, Cascade will call the Abridge (AI Clinical Documentation API) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "abridge-ai-clinical-documentation-api-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 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 Windsurf

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server configuration under the `mcpServers` key. Alternatively, use the Settings UI under Cascade to add the server URL. Once you click refresh, Cascade instantly registers the clinical tools.

Yes, Cascade handles the file paths and passes them to the `create_recording` tool. It monitors the upload progress and handles the file transfer in the background. You don't need to manually chunk the audio.

Cascade loops the `get_recording_status` tool to check if the state has shifted from pending to completed. It does this autonomously in the background. You get a notification the second the structured text is ready.

The `get_clinical_notes` tool delivers structured JSON containing distinct fields for HPI, physical exams, and assessment plans. Cascade parses this structure to populate your files. You can direct it to format the output into markdown or custom EHR layouts.

All patient audio files and clinical notes process inside a secure, zero-trust V8 sandbox environment. Vinkius manages the authentication tokens so your local IDE never exposes raw credentials. Your clinical data is encrypted in transit and deleted from ephemeral memory immediately after processing.

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