How to Use the Harvard ClinicalTrials MCP in LlamaIndex

Q: Can I index trial results from Harvard ClinicalTrials into a LlamaIndex vector store?

Yes. You can use the getstudyresults tool to fetch raw outcome data, convert the resulting JSON into LlamaIndex Document objects, and insert them directly into your vector index for semantic search.

Q: Can LlamaIndex agents filter which Harvard ClinicalTrials tools they use?

Yes, you can use the allowedtools filter in LlamaIndex to restrict your agent's access. For example, you can limit an agent to only use searchrarediseases and getstudy to keep its focus tight.

Q: How do I find trials in specific geographic regions?

Use the searchbylocation tool within your indexing pipeline. This lets you filter trials by country, state, or city, allowing your RAG application to answer location-specific enrollment questions.

Index live clinical trial data directly into your LlamaIndex vector stores 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 LlamaIndex

Create your Vinkius account to connect Harvard ClinicalTrials to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn live trial data into queryable vector indexes

Feed structured trial data directly into your RAG pipelines without manually scraping registries. By wrapping this server with LlamaIndex, tools like `get_study` and `get_study_results` fetch raw trial payloads that your pipeline can immediately parse, chunk, and index. This keeps your vector store grounded in current clinical facts rather than static, outdated documents. You can write query engines that semantic-search across these indexed trial documents. When a user asks about active studies, your pipeline queries the vector store, detects gaps, and uses `search_recruiting` to fetch and index the missing pieces in real time.

Ground LlamaIndex RAG applications in real clinical data

Avoid model hallucinations when building medical search applications. By connecting this MCP Server, your LlamaIndex query engines can retrieve verified registry data on demand. Use `search_by_condition` to find trials for specific diseases, and use the returned data to synthesize answers backed by actual NCT IDs. This MCP Server integration handles schema translation automatically. The McpToolSpec maps the server's sixteen tools directly to LlamaIndex tool specs, making them immediately available to your function-calling agents and query pipelines.

Filter and index trials by phase and drug type

Build specialized clinical indexes by targeting specific trial types. Your indexing scripts can run `search_by_intervention` to pull trials for specific compounds, or use `search_fda_regulated` to isolate high-standard drug trials. This lets you build highly curated knowledge bases for specific therapeutic areas. For tracking trial progress, use `get_study_timeline` to feed status changes directly into your index. This ensures your research tools always reflect the actual, current state of ongoing clinical investigations.

Setup guide

Set up Harvard ClinicalTrials MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Harvard ClinicalTrials MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Harvard ClinicalTrials tools.",
)
response = await agent.run("List recent Harvard ClinicalTrials data")

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 LlamaIndex

Yes. You can use the `get_study_results` tool to fetch raw outcome data, convert the resulting JSON into LlamaIndex Document objects, and insert them directly into your vector index for semantic search.

Initialize the basic MCP client with your Vinkius endpoint, wrap it in an McpToolSpec, and call to_tool_list_async. You can then pass these tools directly to a LlamaIndex FunctionAgent or query engine.

Yes, you can use the allowed_tools filter in LlamaIndex to restrict your agent's access. For example, you can limit an agent to only use `search_rare_diseases` and `get_study` to keep its focus tight.

Use the `search_by_location` tool within your indexing pipeline. This lets you filter trials by country, state, or city, allowing your RAG application to answer location-specific enrollment questions.

The server strictly processes public registry fields, study locations, and investigator names. All data transit is encrypted via HTTPS through the Vinkius sandbox, ensuring no proprietary research queries or internal search histories leak to external parties.

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