How to Use the EBI PDBe MCP in Google ADK

Q: Can Google ADK agents filter specific EBI PDBe structural tools?

Yes, you can use the toolnames parameter to restrict access. For instance, you can expose only getsummary and getqualityscores to keep your Google ADK agent focused on quality control of EBI PDBe entries.

Q: Does the EBI PDBe MCP server support long-context reasoning in Google ADK?

Yes, the EBI PDBe server returns rich structural data like getresiduelisting which fits perfectly into Gemini's large context window. This allows the Google ADK agent to analyze entire protein chains in a single turn.

Q: How do I extract experimental details?

Use getexperiment to retrieve the exact physical methods used to solve the structure. This helps your Google ADK agent evaluate if the data comes from X-ray crystallography or cryo-EM.

Feed high-resolution 3D macromolecular data directly to your Google ADK enterprise agents for large-scale analysis.

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 Google ADK

Create your Vinkius account to connect EBI PDBe to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise structure searching with Google ADK

The `search_structures` tool runs natural language queries across the database to find specific target proteins. Your Google ADK agent parses these MCP search results to feed downstream pipelines. You can filter by resolution or experimental method in real-time. This lets your Google ADK agent build clean datasets for machine learning models on Vertex AI.

Quaternary structure analysis on the MCP Server

The `get_assemblies` tool checks whether a protein operates as a monomer, dimer, or larger complex. Your Google ADK agent uses this structural information to model realistic protein-protein interactions. The tool outputs exact composition and preferred assembly flags from the EBI PDBe database. This ensures your Google ADK workflows analyze the actual biological unit rather than an artifact of crystallization.

Mapping functional cofactors

The `get_cofactors` tool identifies essential non-protein components like heme or metal ions bound to the target. Your Google ADK agent needs this chemical context from EBI PDBe to model catalytic activity accurately. The Google ADK agent combines this with `get_modified_residues` to detect post-translational modifications. This gives your pipeline a complete picture of the active enzyme state.

Setup guide

Set up EBI PDBe MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with EBI PDBe tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="EBI PDBe_agent",
    model="gemini-2.0-flash",
    instruction="You have access to EBI PDBe tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate McpToolset with the streamable HTTP endpoint. Pass this toolset directly to your Google ADK LlmAgent to let Gemini call the structural biology tools.

Yes, you can use the tool_names parameter to restrict access. For instance, you can expose only `get_summary` and `get_quality_scores` to keep your Google ADK agent focused on quality control of EBI PDBe entries.

Yes, the EBI PDBe server returns rich structural data like `get_residue_listing` which fits perfectly into Gemini's large context window. This allows the Google ADK agent to analyze entire protein chains in a single turn.

Use `get_experiment` to retrieve the exact physical methods used to solve the structure. This helps your Google ADK agent evaluate if the data comes from X-ray crystallography or cryo-EM.

All EBI PDBe queries, chemical formulas, and UniProt IDs remain within your private Google Cloud and Vinkius runtime boundary. No coordinate data is ever exposed to public training sets.

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