How to Use the FishBase MCP in AutoGen

Q: How do AutoGen agents access the FishBase tools?

You register the tools using mcpservertools and pass the resulting list to your AssistantAgent constructor. This exposes all 5 marine database tools to the agents in your conversation group.

Q: Can an AutoGen agent check FishBase API versions?

Yes, the agent can call getversions during its planning phase to determine which database release is currently active. It then shares this version number with other agents in the group to maintain consistency.

Let AutoGen agents debate and verify marine taxonomy using live FishBase data.

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 AutoGen

Create your Vinkius account to connect FishBase to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve taxonomic conflicts via AutoGen debates

The `list_comnames` tool provides the factual foundation when your research agent and data verification agent debate fish classifications. One agent queries the common names database while the other checks for naming collisions. This consensus-driven workflow ensures that only verified common names make it into your final reports. The agents use the `McpToolAdapter` to automatically format the JSON payloads during their conversation.

Verify API health before multi-agent tasks

The `get_heartbeat` tool allows your AutoGen orchestrator to check server availability before starting a complex multi-agent discussion. If the endpoint is down, the supervisor agent pauses the workflow to prevent execution errors. This check runs in the background using the Streamable HTTP transport. By verifying the API status early, you avoid wasting compute cycles on agents waiting for unresponsive database endpoints.

AutoGen agents read schemas to build queries

The `get_docs_by_table` tool gives your coder agent the exact database schema needed to construct SQL queries. Instead of guessing table structures, the agent inspects the documentation metadata directly. A separate critic agent then reviews the constructed query against the schema returned by `get_docs`. This collaborative process eliminates syntax errors before any commands are executed against this MCP Server.

Setup guide

Set up FishBase MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes FishBase tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="FishBase_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent FishBase data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="FishBase_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent FishBase data")
    print(result.messages[-1].content)

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 AutoGen

You register the tools using `mcp_server_tools` and pass the resulting list to your `AssistantAgent` constructor. This exposes all 5 marine database tools to the agents in your conversation group.

Yes, the agent can call `get_versions` during its planning phase to determine which database release is currently active. It then shares this version number with other agents in the group to maintain consistency.

You configure execution delays or retry logic within your AutoGen agent's tool execution environment. Since the agents call `list_comnames` during their debates, rate limiting prevents them from spamming the API.

The server runs over Streamable HTTP or stdio transports managed by Vinkius. The `McpToolAdapter` handles all schema conversions, making the tools compatible with AutoGen's internal execution format.

Your Vinkius endpoint token is handled strictly within an isolated environment variables layer and is never exposed to the AutoGen agents. The agents only interact with the tool schemas, keeping your credentials completely hidden.

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