How to Use the FishBase MCP in OpenAI Agents SDK

Q: How does FishBase integrate with OpenAI Agents SDK?

You register the MCP server in your python code using MCPServerStreamableHttp and pass it to your agent constructor. The agent automatically discovers tools like listcomnames and queries them during conversations.

Q: How does the OpenAI Agents SDK handle schema changes in FishBase?

The agent uses getdocsbytable to inspect current table schemas at runtime. This dynamic lookup prevents your python code from breaking when the underlying database structure updates.

Q: What is the best way to handle pagination with this MCP server?

When calling listcomnames, your agent should inspect the pagination parameters returned by the tool. You can configure the agent's system prompt to loop through pages sequentially until all records are retrieved.

Feed live fish taxonomy directly to your OpenAI Agents SDK workflows without manually scraping marine databases.

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 OpenAI Agents SDK

Create your Vinkius account to connect FishBase to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify API health inside OpenAI Agents SDK

Before running heavy taxonomic searches, your agent can ping the live database using `get_heartbeat`. This prevents your pipeline from hanging on dead endpoints or wasting tokens on unresponsive servers. The agent checks the API response time and status first. If the connection fails, the SDK handles the fallback immediately before executing downstream tasks.

Discover schema metadata with this MCP Server

Let your OpenAI Agents SDK inspect table structures on the fly with `get_docs` and `get_docs_by_table`. Your agent reads the exact schema definition to construct precise queries without guessing column names. Instead of hardcoding database schemas, the agent queries the documentation dynamically. This keeps your marine search pipelines accurate even when database tables update.

Extract common fish names in real-time

Your agent pulls regional common names using `list_comnames` to map local terms to scientific classifications. The tool handles pagination automatically, letting your agent parse massive datasets in chunks. By querying `get_versions` via the MCP server, your OpenAI Agents SDK checks which database release it is querying. This ensures taxonomic classifications remain consistent across different research papers.

Setup guide

Set up FishBase MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all FishBase tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives FishBase tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate FishBase tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="FishBase Agent",
            instructions="You have access to FishBase tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You register the MCP server in your python code using `MCPServerStreamableHttp` and pass it to your agent constructor. The agent automatically discovers tools like `list_comnames` and queries them during conversations.

Yes, you can control tool access by filtering the tool list before passing it to the agent constructor. This prevents the agent from running unnecessary checks like `get_heartbeat` if it only needs taxonomic data.

The agent uses `get_docs_by_table` to inspect current table schemas at runtime. This dynamic lookup prevents your python code from breaking when the underlying database structure updates.

When calling `list_comnames`, your agent should inspect the pagination parameters returned by the tool. You can configure the agent's system prompt to loop through pages sequentially until all records are retrieved.

This server only queries public marine taxonomy data and common names. No personal user data is ever sent to the external API, and the Vinkius sandbox keeps your API endpoint tokens isolated.

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