How to Use the Harvard ClinicalTrials MCP in Google ADK

Q: How do I configure Google ADK to use the Harvard ClinicalTrials MCP Server?

Initialize a McpToolset with your HTTP endpoint using StreamableHttpServerParameters. Pass that toolset into your LlmAgent constructor to expose the tools.

Q: Can Gemini agents query Harvard ClinicalTrials for specific study phases?

They can use the searchbyphase tool to filter exactly what you need. You just ask the agent to find Phase 3 or early Phase 1 trials, and it maps the request to the correct API payload.

Q: How do I verify the trial data is current?

Instruct your agent to call getapiversion. It returns the exact timestamp of the most recent database update from the government registry.

Feed Harvard ClinicalTrials data directly into Google ADK. Give your Gemini agents access to global trial registries for deep medical analysis.

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 Google ADK

Create your Vinkius account to connect Harvard ClinicalTrials 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 Harvard ClinicalTrials with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze global registries with this MCP Server

This MCP Server connects your Google ADK environment to a massive registry of global medical studies. Your Gemini agents use `search_studies` to pull hundreds of trial records, taking advantage of the model's massive 1M+ token context window to read them all at once. You can pipe the output directly into BigQuery. An agent can run `search_rare_diseases` to find niche studies, then format the raw JSON into a structured table for your data science team to query on Google Cloud.

Cross-reference geographic trial locations

Finding active research requires the `search_recruiting` and `search_by_location` tools. Your agent cross-references geographic patient data against trials that are actively accepting new participants. Google ADK handles the routing automatically. If you restrict the exposed tools using the `tool_names` filter, you can force a specific agent to only use `search_device_trials` and ignore drug-based interventions. This keeps specialized agents focused on their exact domain.

Extract historical trial outcomes

Historical outcome analysis relies on the `search_completed` and `get_study_results` tools. Gemini can read through years of Phase 3 and Phase 4 trial outcomes to identify success patterns across different sponsors. Connecting this MCP requires just a few lines of Python. You initialize a `McpToolset` with your server URL, pass it to your `LlmAgent`, and the system is ready to pull timeline data via `get_study_timeline`.

Setup guide

Set up Harvard ClinicalTrials 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 Harvard ClinicalTrials 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="Harvard ClinicalTrials_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Harvard ClinicalTrials 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 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 Google ADK

Initialize a `McpToolset` with your HTTP endpoint using `StreamableHttpServerParameters`. Pass that toolset into your `LlmAgent` constructor to expose the tools.

They can use the `search_by_phase` tool to filter exactly what you need. You just ask the agent to find Phase 3 or early Phase 1 trials, and it maps the request to the correct API payload.

The framework itself processes the live responses from tools like `get_study`. If you want to store the trial data long-term, you should have your agent write the output directly to Vertex AI or BigQuery.

Instruct your agent to call `get_api_version`. It returns the exact timestamp of the most recent database update from the government registry.

The server strictly processes public trial parameters like medical conditions, drug interventions, and geographic locations. Every tool execution runs inside a zero-trust sandbox, ensuring your proprietary Gemini prompts and specific research targets vanish the moment the session ends.

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