How to Use the ClinicalTrials.gov MCP in CrewAI

Q: How do I restrict certain CrewAI agents from accessing ClinicalTrials.gov?

Use the MCPServerHTTP class with a toolfilter. This lets you expose the search functions to one agent while hiding them from others.

Deploy specialized CrewAI agents using the ClinicalTrials.gov MCP Server to monitor, analyze, and match patients autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClinicalTrials.gov MCP to CrewAI

Create your Vinkius account to connect ClinicalTrials.gov to CrewAI 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 ClinicalTrials.gov with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate medical research crews

A single agent chokes on a thousand study protocols. Assign `search_clinical_trials` to a dedicated researcher that hunts down databases using condition keywords. That researcher passes raw hits to an analyst agent who reads the inclusion criteria. The workload splits across specialized roles instead of breaking a single prompt.

Track enrollments with the MCP Server

Tracking open sites is a full-time job. A monitor agent runs `find_recruiting_trials` on a loop to spot new patient opportunities the moment they hit the registry. When a match appears, a moderator agent verifies the location data and escalates the finding to a human coordinator. Your crew handles the tedious monitoring autonomously.

Analyze NCT records in parallel

Complex medical reviews require deep context. Give your senior medical agent access to `get_trial_details` so it can pull the complete registry entry for any promising study. Shared memory allows the entire crew to reference the exact same trial parameters. They debate the viability of the experimental therapy based on hard data, not hallucinations.

Setup guide

Set up ClinicalTrials.gov MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ClinicalTrials.gov tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ClinicalTrials.gov Analyst",
    goal="Access and analyze ClinicalTrials.gov data via MCP.",
    backstory="Expert analyst with direct ClinicalTrials.gov access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ClinicalTrials.gov transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ClinicalTrials.gov Analyst",
        goal="Access and analyze ClinicalTrials.gov data via MCP.",
        backstory="Expert analyst with direct ClinicalTrials.gov access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ClinicalTrials.gov transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 ClinicalTrials.gov 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 ClinicalTrials.gov MCP in CrewAI

Pass your Vinkius endpoint URL directly into the mcps array in your agent definition. The framework automatically parses the available tools and equips your crew.

Yes, but you should assign specific tools to specific roles. A researcher handles the broad searches while an analyst pulls individual NCT records to prevent redundant API calls.

The built-in memory system tracks previous tool executions. If an agent already pulled an NCT record, the crew references the cached data instead of hitting the registry again.

Use the MCPServerHTTP class with a tool_filter. This lets you expose the search functions to one agent while hiding them from others.

Vinkius processes your crew's requests through ephemeral sandboxes. Medical condition inputs and drug names vanish immediately after the MCP tool returns the data, protecting sensitive research parameters.

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