How to Use the EBI PDBe MCP in LlamaIndex

Q: Can I filter which MCP tools are exposed to my LlamaIndex agent?

Yes, you use the allowedtools filter in the client setup. This lets you restrict your agent to specific operations, like only allowing getqualityscores and getexperiment for quality control pipelines.

Index 3D macromolecular structures directly into LlamaIndex vector stores to ground your biology queries in verified PDB data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EBI PDBe MCP to LlamaIndex

Create your Vinkius account to connect EBI PDBe 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 EBI PDBe with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG Indexes with MCP Structural Data

`get_summary` fetches the core structural metadata, including resolution and experimental methods, for any target protein. LlamaIndex takes this raw JSON output and indexes it directly into your vector database, making the structural metadata searchable. This approach turns transient API responses into a persistent, queryable knowledge base. Your agent queries this index to retrieve past structural summaries without making repeated network calls to the external registry.

Index Ligand and Residue Interactions

`get_binding_sites` extracts precise residue positions and chemical interactions for bound cofactors. LlamaIndex parses these interaction profiles, chunking the data so your RAG pipeline can reference specific binding pockets during semantic search. Combining this tool with `get_ligand_monomers` allows you to build a local index of small-molecule binding configurations. Your agent can then answer complex questions about binding site conservation using actual coordinate data.

Ground Biology Queries in Verified Assemblies

`get_assemblies` verifies the biological unit of a protein, showing whether it operates as a monomer or a larger complex. LlamaIndex stores these assembly configurations alongside sequence mapping data retrieved via `get_uniprot_mapping`. This grounding prevents your agent from hallucinating quaternary structures during natural language queries. The system verifies every structural claim against the physical properties provided by this MCP Server.

Setup guide

Set up EBI PDBe 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 EBI PDBe 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 EBI PDBe tools.",
)
response = await agent.run("List recent EBI PDBe 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 PDBe (Protein Data Bank in Europe). 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 EBI PDBe 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 EBI PDBe MCP in LlamaIndex

Install llama-index-tools-mcp and initialize the BasicMCPClient. Wrap it in McpToolSpec to retrieve tools like get_summary, then load the tool outputs directly into your document index.

Yes. By passing the tools from McpToolSpec to a FunctionAgent, your agent can choose to run search_structures or get_quality_scores to answer specific user questions on the fly.

The agent is forced to pull raw structural data from tools like get_molecules or get_sequence before answering. This grounds the response in physical database records rather than the parametric memory of the LLM.

Yes, you use the allowed_tools filter in the client setup. This lets you restrict your agent to specific operations, like only allowing get_quality_scores and get_experiment for quality control pipelines.

Yes. Your sequence queries and PDB IDs are processed in an ephemeral Vinkius sandbox. The data is sent securely to EBI PDBe to fetch mappings, and no structural files are cached or exposed to external networks.

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