How to Use the EBI InterPro MCP in Google ADK

Q: How do I initialize the EBI InterPro MCP Server inside the Google ADK?

You initialize it by instantiating McpToolset with StreamableHttpServerParameters pointing to your Vinkius HTTP endpoint. Pass this toolset object into your LlmAgent constructor to expose all 16 bioinformatic tools to Gemini.

Q: Can a Google ADK agent cross-reference EBI InterPro data with BigQuery?

Yes, your agent can query public EBI data via getentry and join it with private sequence tables in BigQuery. Gemini uses its long-context reasoning to analyze the combined datasets in a single execution step.

Q: What is the best way to resolve Pfam clan groupings inside a Google ADK workflow?

Your agent should call getclan with a Pfam clan accession like CL0001. This returns the member counts and description, which helps your agent organize individual domains into broader superfamilies.

Connect the Google ADK to EBI InterPro to analyze massive proteome datasets using Gemini long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EBI InterPro MCP to Google ADK

Create your Vinkius account to connect EBI InterPro 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 InterPro with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query massive proteomes using Google ADK agents

The `get_proteome` tool pulls domain coverage statistics and protein counts for reference proteomes directly into your Google ADK agent. Your Google ADK agent calls this tool to ingest whole-organism datasets, feeding the raw metrics directly into Gemini's million-token context window. By combining this proteome tool with BigQuery datasets, your Google ADK agent runs comparative genomics at scale. The ADK's native Google Cloud integration means you can pipe these EBI InterPro proteome statistics straight into your enterprise data pipelines without writing custom glue code.

Map structural variants using this genomic MCP Server

The `get_structure` tool retrieves specific PDB structures decorated with mapped InterPro annotations for your Google ADK pipelines. Your Google ADK setup uses this tool to ground Gemini's structural reasoning in verified physical data, bypassing the hallucination risks of raw text models. When your Google ADK pipeline needs to scale down to individual domains, it triggers `get_pfam_entry` to fetch Pfam-specific alignments. You filter these EBI InterPro tools using the ADK's optional tool name filter, exposing only the precise structural endpoints your cloud agent requires.

Track evolutionary lineages across enterprise databases

The `search_taxonomy` tool locates specific taxon IDs and organism ranks within the EBI database for Google ADK workflows. Google ADK agents use this tool to verify taxonomic classifications before saving annotated records back to your Vertex AI feature store using this MCP connection. To map wider evolutionary relationships, the Google ADK agent calls `get_taxonomy` to retrieve lineage structures and child counts. This lets your enterprise Google ADK agent build clean phylogenetic trees, matching private sequence databases with public EBI InterPro evolutionary records.

Setup guide

Set up EBI InterPro 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 InterPro 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 InterPro_agent",
    model="gemini-2.0-flash",
    instruction="You have access to EBI InterPro 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 InterPro. 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 InterPro 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 InterPro MCP in Google ADK

You initialize it by instantiating `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius HTTP endpoint. Pass this toolset object into your `LlmAgent` constructor to expose all 16 bioinformatic tools to Gemini.

Yes, your agent can query public EBI data via `get_entry` and join it with private sequence tables in BigQuery. Gemini uses its long-context reasoning to analyze the combined datasets in a single execution step.

You restrict them by passing a list of allowed tool names to your `McpToolset` configuration. For example, you can expose only `get_protein` and `get_protein_entries` if your agent only needs sequence-to-domain mapping.

Your agent should call `get_clan` with a Pfam clan accession like CL0001. This returns the member counts and description, which helps your agent organize individual domains into broader superfamilies.

All taxonomy IDs and protein names travel over encrypted TLS channels directly to the isolated Vinkius MCP runtime. The server runs inside zero-trust, ephemeral V8 sandboxes that isolate your biological queries from other cloud workloads.

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