How to Use the Abridge (AI Clinical Documentation API) MCP in OpenAI Agents SDK

Q: How do I connect the Abridge (AI Clinical Documentation API) server to my OpenAI Agents SDK project?

First, pip install openai-agents. Then, you'll instantiate MCPServerStreamableHttp with the endpoint URL from your Vinkius dashboard. Just pass that server object into the mcpservers list when you create your agent.

Q: Does this work with specialized agent handoffs?

Absolutely. A 'recorder' agent can handle the createrecording and getrecordingstatus loop. Once the status is completed, it can hand off the recording ID to a 'charting' agent that calls getclinicalnotes to process the structured data.

Build production-grade clinical documentation agents with built-in safety checks using the OpenAI Agents SDK and Abridge's MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Abridge (AI Clinical Documentation API) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Upload Audio or Start Live Recordings

This MCP Server gives your agent a `create_recording` tool to start the clinical note generation process. You can point it to an existing audio file or have it create a new recording session on the fly. It's a direct way to get patient conversations into the Abridge system. Here’s where the OpenAI Agents SDK helps. Its built-in guardrails let you validate the request *before* the `create_recording` tool executes. This means your agent system can enforce rules—like checking audio metadata or confirming patient consent—preventing bad data from ever hitting the API.

Check Note Generation Progress

Your agent can use the `get_recording_status` tool to check on a documentation job. You don't have to guess. The tool returns a clear status: `pending`, `processing`, `completed`, or `failed`, so your agent knows exactly what to do next. This is much easier to debug with the OpenAI SDK's tracing features. Every call your agent makes to `get_recording_status` is logged in your OpenAI dashboard. When you're debugging a complex agent that waits for a note to finish, you get a clear, step-by-step view of the entire process.

Pull Structured Notes into Your Agent

Once a recording is processed, your agent calls `get_clinical_notes` to get the results. This isn't just a block of text. You get structured data, including the summary, HPI, physical exam, and assessment plan, all broken out into separate fields. This structured data is perfect for the OpenAI SDK's agent handoff feature. For example, one agent can use this tool to fetch the note, then pass the structured data to a second, specialized agent for billing code analysis or patient follow-up tasks. The clean data from this MCP Server makes those handoffs reliable.

Setup guide

Set up Abridge (AI Clinical Documentation API) MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Abridge (AI Clinical Documentation API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Abridge (AI Clinical Documentation API) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Abridge (AI Clinical Documentation API) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Abridge (AI Clinical Documentation API) Agent",
            instructions="You have access to Abridge (AI Clinical Documentation API) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

First, `pip install openai-agents`. Then, you'll instantiate `MCPServerStreamableHttp` with the endpoint URL from your Vinkius dashboard. Just pass that server object into the `mcp_servers` list when you create your agent.

Yes, tool discovery is automatic. As soon as you connect the MCP Server, your agent will see the `create_recording`, `get_recording_status`, and `get_clinical_notes` tools without any manual coding. For better performance in production, set `cacheToolsList=True` so it doesn't re-discover them on every startup.

Safety and observability. OpenAI's guardrails let you check parameters before your agent calls an Abridge tool, preventing errors. Plus, the full execution trace in the OpenAI dashboard shows you exactly how your agent is interacting with the clinical documentation API, which makes debugging much faster.

Absolutely. A 'recorder' agent can handle the `create_recording` and `get_recording_status` loop. Once the status is `completed`, it can hand off the recording ID to a 'charting' agent that calls `get_clinical_notes` to process the structured data.

Your agent sends audio data through the Vinkius MCP Server, which acts as a secure proxy to the Abridge API. The server itself is ephemeral and runs in a zero-trust sandbox. It only handles the transaction and does not store your clinical audio files.

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