How to Use the PMC Open Access (PubMed Central) MCP in LlamaIndex

Q: Can I use PMC Open Access (PubMed Central) to build a medical RAG pipeline in LlamaIndex?

Yes. Use oaigetrecord to retrieve full XML payloads, then parse and index them into a LlamaIndex vector store for semantic querying.

Q: How does LlamaIndex handle ID mapping with PMC Open Access (PubMed Central)?

The framework calls convertids to resolve PMIDs and DOIs into unified PMCIDs. This ensures all your indexed metadata points to the correct, unique paper.

Q: Can LlamaIndex fetch full-text PDFs from the PMC Open Access (PubMed Central) subset?

LlamaIndex uses oadiscover to retrieve the direct download URLs for open-access articles. You can then pass these URLs to a PDF reader to ingest the full text.

Q: Does this server support structured metadata filtering in LlamaIndex?

Yes. You can query metadata formats using oailistmetadataformats to ensure your LlamaIndex node parsers match the incoming XML structure.

Index PMC Open Access (PubMed Central) metadata directly into LlamaIndex vector stores for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PMC Open Access (PubMed Central) MCP to LlamaIndex

Create your Vinkius account to connect PMC Open Access (PubMed Central) to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PMC Open Access (PubMed Central) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Grounding LlamaIndex RAG in PubMed Central Data

Stop letting your LLM guess clinical facts in LlamaIndex. This MCP Server lets LlamaIndex query `oai_get_record` to fetch verified XML metadata, then indexes that raw text directly into your local vector database. Your LlamaIndex agent queries the index using semantic search. Because the source data is grounded in actual PMC records, you eliminate hallucinations and keep your clinical applications accurate.

Dynamic ID Resolution for Vector Stores

If your local LlamaIndex database uses mixed citation formats, it ruins semantic retrieval. LlamaIndex resolves this by running `convert_ids` to map PMIDs, DOIs, and PMCIDs to a single standard before indexing. This ensures your LlamaIndex vector nodes map to the correct source documents. The agent queries `oa_discover` to fetch the actual open-access PDF URLs, appending them as metadata to your index nodes.

Structured Metadata Harvesting

Building a clean medical knowledge base in LlamaIndex requires highly structured input. LlamaIndex uses `oai_list_metadata_formats` to discover the exact schemas available before pulling records. The agent then runs `oai_list_records` to harvest bulk PubMed Central articles. It structures the incoming XML into indexable LlamaIndex document nodes, keeping your local knowledge base fresh.

Setup guide

Set up PMC Open Access (PubMed Central) 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 PMC Open Access (PubMed Central) 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 PMC Open Access (PubMed Central) tools.",
)
response = await agent.run("List recent PMC Open Access (PubMed Central) 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 PMC (PubMed Central). 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 PMC Open Access (PubMed Central) 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 PMC Open Access (PubMed Central) MCP in LlamaIndex

Yes. Use `oai_get_record` to retrieve full XML payloads, then parse and index them into a LlamaIndex vector store for semantic querying.

The framework calls `convert_ids` to resolve PMIDs and DOIs into unified PMCIDs. This ensures all your indexed metadata points to the correct, unique paper.

LlamaIndex uses `oa_discover` to retrieve the direct download URLs for open-access articles. You can then pass these URLs to a PDF reader to ingest the full text.

Yes. You can query metadata formats using `oai_list_metadata_formats` to ensure your LlamaIndex node parsers match the incoming XML structure.

The PMC IDs and metadata queries flow through a zero-trust, ephemeral V8 isolate container. Your proprietary medical queries and search terms never touch persistent storage.

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