How to Use the GenBank/NCBI API MCP in Google ADK

Q: How do I connect the GenBank/NCBI API to a Gemini agent using the Google ADK?

Install the google-adk library and create an McpToolset instance pointing to your Vinkius MCP Server URL. You then pass this toolset to your LlmAgent to give it immediate access to the NCBI tools.

Q: What's the best way to manage tool access with Google ADK and the GenBank/NCBI API?

Use the toolnames parameter when you initialize the McpToolset. This lets you create specialized agents. You can build one agent that only monitors status and another that only performs searches.

Q: How do I find out which databases are available to search?

Your agent can call the listncbidatabases tool. This returns a current list of all queryable databases, such as 'nuccore' or 'protein', which you can then use in your searchncbisequences calls.

Connect your Google ADK agent to live genomic data. Query NCBI from your Gemini-powered, long-context agent on Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GenBank/NCBI API MCP to Google ADK

Create your Vinkius account to connect GenBank/NCBI API 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 GenBank/NCBI API with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query NCBI from Your Google Cloud Agent

This MCP Server connects your GCP environment directly to external biological data. An `LlmAgent` running on Vertex AI can now use the `McpToolset` to interact with the NCBI API, querying public databases from within your private cloud. Imagine your agent pulling a list of target genes from a BigQuery table. It can then immediately use `search_ncbi_sequences` to find their UIDs in GenBank. It's a straight line from your data to public scientific resources.

Filter and Summarize with Long Context

Gemini's long context window is ideal for bioinformatics work. Your agent can run a broad `search_ncbi_sequences` query that returns thousands of UIDs and hold the entire list in its context for analysis. From there, the agent can reason about the results. It can iterate through the UIDs and call `get_ncbi_summary` for each one, gathering metadata to decide which sequences are actually worth a deeper look. This all happens without breaking context or writing to disk.

Selectively Expose NCBI Tools

The Google ADK gives you fine-grained control over your agent's capabilities. When you configure the `McpToolset`, you can use the `tool_names` filter to expose only the functions you want the agent to have. For example, you could build a simple monitoring agent that only has access to `check_api_status`. Or, create a research agent that can `search_ncbi_sequences` but can't perform other actions. You decide exactly what the agent is allowed to do.

Setup guide

Set up GenBank/NCBI API 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 GenBank/NCBI API 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="GenBank/NCBI API_agent",
    model="gemini-2.0-flash",
    instruction="You have access to GenBank/NCBI API 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 GenBank/NCBI. 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 GenBank/NCBI API 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 GenBank/NCBI API MCP in Google ADK

Install the `google-adk` library and create an `McpToolset` instance pointing to your Vinkius MCP Server URL. You then pass this toolset to your `LlmAgent` to give it immediate access to the NCBI tools.

Yes, it's a perfect fit. Gemini's long-context window allows your agent to run a `search_ncbi_sequences` query, hold hundreds or thousands of UIDs in memory, and then reason about which ones to process further with `get_ncbi_summary`.

Use the `tool_names` parameter when you initialize the `McpToolset`. This lets you create specialized agents. You can build one agent that only monitors status and another that only performs searches.

Your agent can call the `list_ncbi_databases` tool. This returns a current list of all queryable databases, such as 'nuccore' or 'protein', which you can then use in your `search_ncbi_sequences` calls.

Your queries, which might include gene names or other non-PHI identifiers, are sent to the NCBI API. Vinkius manages the secure channel, and all data processing happens within your agent's context inside your Google Cloud environment.

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