How to Use the Harvard ClinicalTrials MCP in OpenAI Agents SDK

Q: How do I connect the Harvard ClinicalTrials MCP Server to the OpenAI Agents SDK?

Use the MCPServerStreamableHttp class with your endpoint URL. Pass it to your agent's mcpservers array and it auto-discovers all 16 tools.

Q: Can the OpenAI Agents SDK filter Harvard ClinicalTrials by specific drugs?

Yes, the system maps directly to the searchbyintervention tool. Your agent can look up exact treatments like metformin or pembrolizumab and return the matching study IDs.

Q: What happens if the government API goes down?

Your agent can check the endpoint status using getapiversion. This returns the current API version and the most recent data timestamp, so your code knows if it has stale data.

Connect OpenAI Agents SDK to 400K+ clinical trials. Build production-ready medical research agents with built-in guardrails and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harvard ClinicalTrials MCP to OpenAI Agents SDK

Create your Vinkius account to connect Harvard ClinicalTrials 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 Harvard ClinicalTrials with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query 400K+ trials with this MCP Server

The Harvard ClinicalTrials MCP Server lets your OpenAI agents pull raw data from over 400,000 global studies. You pass `search_studies` into your agent's toolkit, and it immediately understands how to query the database by condition, intervention, or location without manual prompt engineering. Because you are running the OpenAI Agents SDK, every query gets logged in your dashboard. You can set up one agent to run `search_by_condition` for rare diseases, and hand off the results to a secondary agent that extracts protocol details using `get_study_results`.

Track exact study timelines and phases

Your agent tracks study progression over time using the `get_study_timeline` tool. This exposes the exact dates for enrollment changes, protocol updates, and completion milestones directly to your Python code. When building medical applications, you need strict guardrails. The SDK validates every action before it executes a `search_by_phase` or `search_fda_regulated` call. If the agent tries to hallucinate a trial ID, the system catches it before making the external request.

Filter for active patient recruitment

Filtering active recruitment requires exact parameters, which `search_recruiting` handles natively. You get immediate access to trials that are actively looking for patients, complete with sponsor details via `search_by_sponsor`. This setup works perfectly for production environments. Set `cacheToolsList=True` in your MCP configuration, and your agents will skip the discovery phase on subsequent runs. They just get straight to parsing pediatric data with `search_pediatric`.

Setup guide

Set up Harvard ClinicalTrials 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 Harvard ClinicalTrials tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Harvard ClinicalTrials tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Harvard ClinicalTrials 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="Harvard ClinicalTrials Agent",
            instructions="You have access to Harvard ClinicalTrials 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 ClinicalTrials.gov. 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 Harvard ClinicalTrials 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 Harvard ClinicalTrials MCP in OpenAI Agents SDK

Use the `MCPServerStreamableHttp` class with your endpoint URL. Pass it to your agent's `mcp_servers` array and it auto-discovers all 16 tools.

Yes, the system maps directly to the `search_by_intervention` tool. Your agent can look up exact treatments like metformin or pembrolizumab and return the matching study IDs.

It works exactly as expected. You can have a researcher agent pull broad data using `search_by_condition`, then hand off specific NCT IDs to an analyst agent to run `get_study` and parse the eligibility criteria.

Your agent can check the endpoint status using `get_api_version`. This returns the current API version and the most recent data timestamp, so your code knows if it has stale data.

The server only touches public clinical trial metadata, like NCT IDs, study phases, and sponsor names. The OpenAI Agents SDK executes these queries through an ephemeral V8 Isolate Sandbox, meaning no request history or patient search parameters are stored on the host after the connection drops.

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