How to Use the FishBase MCP in Google ADK

Q: How do I register the FishBase server in Google ADK?

You initialize the toolset using McpToolset with the HTTP transport URL. Then, pass this toolset to your LlmAgent configuration so Gemini can access tools like listcomnames.

Q: Does Google ADK support all 5 tools of the FishBase MCP Server?

Yes, the framework exposes all five endpoints, including getheartbeat and getversions. You can restrict this list by passing a specific array of tool names to your configuration.

Q: How does Google ADK handle high-volume taxonomic queries from FishBase?

The agent uses the pagination parameters built into listcomnames to fetch records in batches. Gemini's large context window allows it to process thousands of fish names in a single step.

Connect Google ADK agents to live marine taxonomy and common names data for enterprise analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FishBase MCP to Google ADK

Create your Vinkius account to connect FishBase 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 FishBase with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map marine data to BigQuery using Google ADK

Your Gemini agent can extract taxonomic records using `list_comnames` and format them for BigQuery ingestion. This bridges the gap between raw web-scale fish databases and your cloud data warehouse. By querying `get_versions`, the agent tags every imported dataset with its specific database release date. This maintains strict data lineage inside your Google Cloud environment.

Verify endpoints before running long-context tasks

When running massive reasoning tasks on millions of tokens, your agent uses `get_heartbeat` to check connection status. This step saves compute costs by avoiding dead API calls midway through a run. The Gemini model verifies the server status before executing complex taxonomic lookups. If the database is offline, the agent halts the pipeline and alerts your team.

Inspect table structures dynamically with this MCP Server

Your agent reads database documentation on the fly using `get_docs` and `get_docs_by_table`. This allows the model to understand the database structure before generating SQL queries or data pipelines. Instead of relying on static definitions, the agent fetches current metadata directly. This ensures your enterprise workflows always target the correct tables.

Setup guide

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

You initialize the toolset using `McpToolset` with the HTTP transport URL. Then, pass this toolset to your `LlmAgent` configuration so Gemini can access tools like `list_comnames`.

Yes, the framework exposes all five endpoints, including `get_heartbeat` and `get_versions`. You can restrict this list by passing a specific array of tool names to your configuration.

The agent uses the pagination parameters built into `list_comnames` to fetch records in batches. Gemini's large context window allows it to process thousands of fish names in a single step.

Yes, the framework supports both Stdio and HTTP transports. For hosted environments on Google Cloud, the HTTP transport managed by Vinkius is the easiest way to connect.

The server only reads public marine species names and API documentation. It never accesses your Google Cloud databases or private BigQuery tables, keeping your internal research data secure.

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