How to Use the EBI PDBe MCP in OpenAI Agents SDK

Q: Can I use EBI PDBe with OpenAI Agents SDK to search for proteins?

Yes, your OpenAI Agents SDK agent uses the searchstructures tool to query the EBI PDBe database using natural language. It returns matching PDB IDs, resolution limits, and source organisms directly to your agent.

Q: How does the OpenAI Agents SDK handle EBI PDBe assembly states?

Your OpenAI Agents SDK agent calls getassemblies to determine if an EBI PDBe protein exists as a monomer or complex. This prevents the agent from making wrong assumptions about active biological units during automated docking setup.

Q: Can I retrieve literature details for a structure?

Yes, calling getpublications returns primary citations and PubMed IDs. This lets your OpenAI Agents SDK agent cross-reference structural data with published experimental papers.

Get real-time macromolecular structures and ligand data directly inside your OpenAI Agents SDK production workflows.

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 OpenAI Agents SDK

Create your Vinkius account to connect EBI PDBe to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structural validation for OpenAI Agents SDK

The `get_quality_scores` tool pulls R-factor and resolution metrics directly into your OpenAI Agents SDK agent's decision loop. This keeps your OpenAI Agents SDK system from running downstream simulations on low-resolution or flawed EBI PDBe structures. Your OpenAI Agents SDK agent checks these raw metrics before triggering deeper structural analysis. You get clean, verifiable experimental data from EBI PDBe without manual checking.

Target identification via EBI PDBe MCP Server

The `get_binding_sites` tool maps active residues and ligand interactions to help your OpenAI Agents SDK agent pinpoint druggable pockets. This tool feeds raw coordinate context from EBI PDBe straight to your OpenAI Agents SDK pipeline. By coupling this with `get_ligand_monomers`, your OpenAI Agents SDK agent system identifies exactly which small molecules bind to specific chain positions. It replaces slow database lookups with direct, programmatic discovery in your agent workflows.

Mapping sequences to 3D coordinates

The `get_uniprot_mapping` tool links UniProt accessions to exact PDB chain coordinates within your automated OpenAI Agents SDK workflow. Your OpenAI Agents SDK setup uses this MCP mapping to bridge genomic sequences with physical 3D structures from EBI PDBe. Your OpenAI Agents SDK agent then runs `get_mutated_residues` to spot engineered mutations in the crystallized construct. This lets you flag structural discrepancies before they mess up your modeling runs.

Setup guide

Set up EBI PDBe MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all EBI PDBe tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives EBI PDBe tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate EBI PDBe tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="EBI PDBe Agent",
            instructions="You have access to EBI PDBe tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and pass the EBI PDBe server URL using MCPServerStreamableHttp. Your OpenAI Agents SDK agent automatically registers the 16 structural tools at runtime without manual schema definitions.

Yes, your OpenAI Agents SDK agent uses the `search_structures` tool to query the EBI PDBe database using natural language. It returns matching PDB IDs, resolution limits, and source organisms directly to your agent.

Your OpenAI Agents SDK agent calls `get_assemblies` to determine if an EBI PDBe protein exists as a monomer or complex. This prevents the agent from making wrong assumptions about active biological units during automated docking setup.

Yes, calling `get_publications` returns primary citations and PubMed IDs. This lets your OpenAI Agents SDK agent cross-reference structural data with published experimental papers.

All PDB IDs, coordinates, and sequence mappings route directly through the secure MCP sandbox. No structural query data or private ligand files are stored or shared with 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