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

Q: How do I set up the Abridge (AI Clinical documentation API) tools in a Google ADK agent?

After you pip install google-adk, create an McpToolset. Inside, you'll define the StreamableHttpServerParameters using your Vinkius server URL. Then just pass that toolset to the tools list when you initialize your LlmAgent.

Q: Can I restrict which Abridge (AI Clinical Documentation API) tools my Google ADK agent can use?

Yes, you can. The McpToolset in Google ADK accepts a toolnames filter. This lets you create specialized agents by explicitly listing which tools, like just getclinicalnotes, the agent is allowed to execute.

Connect your Gemini agents on Google ADK to clinical documentation. Turn conversations into structured data ready for BigQuery.

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 Google ADK

Create your Vinkius account to connect Abridge (AI Clinical Documentation API) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Abridge from Google Cloud

This MCP Server exposes a `create_recording` tool for your Google ADK agent. It can use this to kick off the documentation process for a new recording. More importantly, it can point to audio files you already have stored in Google Cloud Storage. This fits perfectly into a Google Cloud workflow. You can have a Gemini agent, running on Google's infrastructure, that's triggered by a new file upload to a GCS bucket. The agent then uses this tool to send that file to Abridge, starting your entire documentation pipeline automatically.

Monitor Note Status at Scale

The `get_recording_status` tool lets your agent poll for the result of a documentation job. Your agent gets a clear status update, so it knows whether to wait, retry, or flag an error for a human to review. It's a simple, reliable way to manage asynchronous tasks. Imagine running thousands of these jobs a day. A Google ADK agent can call `get_recording_status` and write the result of each job directly to a BigQuery table. This gives you a real-time operations dashboard of your entire clinical documentation workload, all orchestrated by your agent.

Load Structured Notes into BigQuery

When a recording is processed, your agent uses `get_clinical_notes` to get the structured medical note. The tool returns the summary, HPI, physical exam, and assessment plan as clean, separate fields, not a single blob of text. This is the key for Google ADK users. Your agent can take the JSON response from the tool and directly insert it as a new row in a BigQuery table. You're not just getting a clinical note; you're building a massive, queryable dataset for analytics or training new models on Vertex AI.

Setup guide

Set up Abridge (AI Clinical Documentation API) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Abridge (AI Clinical Documentation API) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Abridge (AI Clinical Documentation API)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Abridge (AI Clinical Documentation API) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

After you `pip install google-adk`, create an `McpToolset`. Inside, you'll define the `StreamableHttpServerParameters` using your Vinkius server URL. Then just pass that toolset to the `tools` list when you initialize your `LlmAgent`.

Yes, you can. The `McpToolset` in Google ADK accepts a `tool_names` filter. This lets you create specialized agents by explicitly listing which tools, like just `get_clinical_notes`, the agent is allowed to execute.

It's all about the deep integration with Google Cloud. Your Gemini agent can natively talk to services like BigQuery and Cloud Storage. That means it can grab an audio file from GCS, send it to Abridge via this MCP Server, and write the final structured note directly into a BigQuery table without any extra glue code.

Definitely. You can build a Google ADK agent that reads a list of file paths from a BigQuery table, loops through them calling `create_recording` for each one, and then uses `get_recording_status` to track all the jobs. It's designed for that kind of batch processing.

The audio data flows from your Google Cloud environment, through the Vinkius MCP Server, to the Abridge API. Vinkius acts as a secure, zero-trust proxy for each transaction but doesn't persist the clinical audio. Your Vinkius token handles authentication, simplifying your security setup.

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