An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Ebi Pdbe to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pull real-time protein and ligand data into your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 16 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 16 available through PDBe (Protein Data Bank in Europe).

  1. 01

    Get cofactors

    This capability retrieves annotations for essential cofactors like heme, NAD+, or metal ions.

  2. 02

    Get experiment

    Use this to pull specific experimental method details for a given structure.

  3. 03

    Get modified residues

    This capability identifies non-standard amino acids and nucleotides, including their parent compound IDs.

  4. 04

    Get molecules

    This capability returns molecular entity data such as chain assignments, sequence lengths, and source organisms.

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 16 available through PDBe (Protein Data Bank in Europe).

  1. 05

    Get mutated residues

    Use this to find engineered mutations and see how a crystallized construct differs from the wild-type sequence.

  2. 06

    Get quality scores

    This capability provides global quality metrics to help you evaluate if a structure is reliable.

  3. 07

    Get related entries

    This capability finds alternative conformations, mutants, or complexes associated with the same publications.

  4. 08

    Get residue listing

    This capability provides a full inventory of residue names and numbers for each chain.

Capability set03 / 04

09-12

4 capabilities in this set.

Part of 16 available through PDBe (Protein Data Bank in Europe).

  1. 09

    Get summary

    Use a 4-character PDB ID to get a quick summary including title, authors, and resolution.

  2. 10

    Get uniprot mapping

    This capability maps UniProt accessions and positions to specific PDB residue numbers.

  3. 11

    Get assemblies

    This capability provides biological assembly information to show if a protein acts as a monomer, dimer, or larger complex.

  4. 12

    Get binding sites

    Use this to identify ligand binding site residues and their specific interactions.

Capability set04 / 04

13-16

4 capabilities in this set.

Part of 16 available through PDBe (Protein Data Bank in Europe).

  1. 13

    Get ligand monomers

    This capability returns chemical component IDs, formulas, and weights for small molecules bound in the structure.

  2. 14

    Get publications

    This capability pulls primary citations and PubMed IDs associated with a structure.

  3. 15

    Get secondary structure

    This capability provides helix, sheet, and coil assignments per residue for each chain.

  4. 16

    Search structures

    Use natural language to search the PDB for specific proteins, organisms, or resolution requirements.

Real work

What teams actually run

01

Rational Drug Design

Identify specific residues in a binding pocket to model how a new small molecule might interact.

02

Protein Engineering

Compare engineered mutations against wild-type sequences using residue-level data.

03

Literature Review

Quickly find the primary PubMed citations and methodology papers for any PDB entry.

04

Structural Characterization

Verify the quaternary structure of a protein to see if it forms dimers or tetramers.

Automate a task

Put PDBe (Protein Data Bank in Europe) to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

PDBe (Protein Data Bank in Europe) works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put PDBe (Protein Data Bank in Europe) to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1047ms average. Fast in production.

PDBe (Protein Data Bank in Europe) is checked daily against the live service.

Daily averagePeak 1232ms
Oct 3Today
Fastest day
731ms
Slowest day
1232ms
14-day trend
Slowing+15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 16 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of PDBe (Protein Data Bank in Europe), so you can see the experience inside your AI.

It does not authenticate your account with PDBe (Protein Data Bank in Europe). Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

PDBe (Protein Data Bank in Europe) Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_bI09khwqGh15yaAARSveb5XxpbscMGTIKjQ4vrCZ/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — PDBe (Protein Data Bank in Europe) capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ebi-pdbe-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_bI09khwqGh15yaAARSveb5XxpbscMGTIKjQ4vrCZ/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up PDBe (Protein Data Bank in Europe) in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work PDBe (Protein Data Bank in Europe) owners hand off.

This MCP is built for researchers working with macromolecular structures who need fast, programmatic access to PDBe data.

  • 01

    Structural Biologists

    They use the AI to pull metadata and experimental parameters without manual browsing.

  • 02

    Drug Discovery Scientists

    They use the AI to identify binding pockets and small molecule interactions for design.

  • 03

    Bioinformaticians

    They use the AI to cross-reference sequence data with 3D structural annotations.

FAQ

Questions PDBe (Protein Data Bank in Europe) owners ask.

  • 01

    Do I need an API key for PDBe?

    No, this MCP uses the public PDBe REST API, so no personal credentials or keys are required.

  • 02

    Which AI clients can use this MCP?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I search for structures using names instead of PDB IDs?

    Yes, the search_structures capability allows you to use natural language queries for protein names or organisms.

  • 04

    How is the data sourced?

    All data is pulled directly from the official PDBe REST API maintained by EMBL-EBI.

  • 05

    Can this help with UniProt data?

    Yes, the MCP includes capabilities to map UniProt sequence positions to specific PDB residues.

  • 06

    Do I need an API key?

    No. The PDBe API is completely public and requires no authentication. Enter any placeholder value in the API key field to activate the server immediately.

  • 07

    What types of structures are available?

    The PDBe contains over 200,000 experimentally determined 3D structures of proteins, nucleic acids, and complex assemblies. Structures are determined by X-ray crystallography, cryo-electron microscopy (cryo-EM), NMR spectroscopy, and other methods. This includes enzymes, receptors, antibodies, viral proteins, ribosomes, and drug-target complexes.

  • 08

    Can I find drug binding sites?

    Yes. Use get_binding_sites to retrieve all annotated ligand binding pockets with their constituent residues. Combine with get_ligand_monomers to identify the small molecules bound in the structure, and get_cofactors for prosthetic groups. This workflow is essential for structure-based drug design and virtual screening target preparation.

Explore

More in The Unthinkable

Suggestions

Connect PDBe (Protein Data Bank in Europe) to Claude, Cursor, ChatGPT & more