How to Use the Harvard ClinicalTrials MCP in AutoGen

Q: How can I search for medical device trials specifically?

Your agents can use the searchdevicetrials tool. This filters the registry to isolate diagnostic tools, surgical implants, and digital health technologies, separating them from drug-based interventions.

Let specialized AutoGen agents debate trial designs and screen studies using the Harvard ClinicalTrials 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 Harvard ClinicalTrials MCP to AutoGen

Create your Vinkius account to connect Harvard ClinicalTrials to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent debates over trial data

Deploy multiple AutoGen agents to analyze clinical trials from different angles. You can set up a clinical trial scout agent that uses `search_by_condition` to find candidate studies, while a regulatory agent uses `search_fda_regulated` to verify compliance. The agents then debate the viability of the trials in a shared chat thread to reach a consensus. This collaborative approach reduces errors in complex research workflows. By separating concerns, one agent can focus on patient recruiting criteria using `search_recruiting` while another evaluates historical outcomes using `get_study_results`, combining their findings into a single, verified report.

Connect AutoGen agents to this medical search MCP Server

Equip your conversational teams with direct access to global clinical registries. By registering this MCP Server with your AutoGen agent configuration, you expose sixteen specialized search tools. Agents can autonomously decide when to call `get_study` or `search_by_intervention` during their multi-turn conversations. The integration uses the AutoGen MCP adapter to handle schema conversion. This ensures that your agents receive clean, structured JSON payloads that they can parse, discuss, and act upon without custom parser code.

Automate pediatric and rare disease trial screening

Build automated screening panels for highly specialized medical fields. Your agents can run `search_rare_diseases` to identify trials for orphan indications, or use `search_pediatric` to filter out adult-only studies. This allows you to build autonomous research pipelines that flag relevant trials the moment they are registered. To track trial evolution, agents can call `get_study_timeline` to monitor protocol amendments and milestone dates. This gives your multi-agent system the context it needs to evaluate whether a study is progressing on schedule.

Setup guide

Set up Harvard ClinicalTrials MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Harvard ClinicalTrials tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Harvard ClinicalTrials_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Harvard ClinicalTrials data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Harvard ClinicalTrials_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Harvard ClinicalTrials data")
    print(result.messages[-1].content)

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 AutoGen

Agents share tool outputs naturally through their conversational context. When one agent runs `search_by_condition`, the resulting trial list is printed to the group chat, allowing other agents to analyze the data.

Yes. You can register the tools with specific agents in your AutoGen group chat. For example, you can give the tools to a Research Agent while keeping a Writer Agent strictly focused on drafting the summary.

The AutoGen MCP adapter automatically converts the server's tool schemas into the format expected by the model. This means tools like `get_study_results` work out of the box without manual JSON schema writing.

Your agents can use the `search_device_trials` tool. This filters the registry to isolate diagnostic tools, surgical implants, and digital health technologies, separating them from drug-based interventions.

The server only accesses public trial endpoints, sponsor names, and enrollment figures. All connections run through an isolated, zero-trust V8 sandbox on Vinkius, ensuring your proprietary screening criteria and agent chat logs are never exposed.

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