How to Use the FishBase MCP in LlamaIndex

Q: How do I index FishBase common names into LlamaIndex?

You call listcomnames using the McpToolSpec to retrieve the raw taxonomic data. Then, you convert this output into LlamaIndex Document objects and write them to your vector store for semantic retrieval.

Q: Can LlamaIndex query FishBase table documentation dynamically?

Yes, your FunctionAgent can call getdocsbytable during a query run to inspect the structure of a specific table. This lets the agent decide how to format its final response based on the retrieved schema.

Q: How do I handle FishBase API versioning in LlamaIndex RAG?

You use getversions to fetch the active database versions and store this value in your node metadata. When a user queries LlamaIndex, the engine filters the vector store to match the requested database version.

Index live FishBase taxonomic data and common names into your LlamaIndex vector stores for accurate RAG.

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 LlamaIndex

Create your Vinkius account to connect FishBase to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable index of fish common names

The `list_comnames` tool extracts common names and taxonomic data directly into your LlamaIndex document pipeline. This data is converted into nodes and indexed in your vector store, allowing semantic search over actual marine databases. Your RAG applications query this local index instead of hitting the live API repeatedly. Grounding your LlamaIndex agent in verified taxonomic records eliminates hallucinated fish names.

Retrieve table schemas for LlamaIndex indexing

The `get_docs_by_table` tool pulls structural documentation for specific marine tables to enrich your LlamaIndex metadata. By indexing these schemas, your agent understands the relationships between different fish datasets before running queries. You use `McpToolSpec` to integrate these documentation tools into your query engines. The engine reads the database structure dynamically to construct precise metadata filters for your vector search.

Track database versions for index consistency

The `get_versions` tool checks the current active database versions to ensure your LlamaIndex knowledge base stays updated. You run this check before initiating a re-indexing job to avoid mixing data from different release cycles. This metadata is appended to your indexed documents as a source attribute. If a taxonomic name changes between versions, your query engine filters results based on the specific database release date.

Setup guide

Set up FishBase MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all FishBase MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to FishBase tools.",
)
response = await agent.run("List recent FishBase data")

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 LlamaIndex

You call `list_comnames` using the `McpToolSpec` to retrieve the raw taxonomic data. Then, you convert this output into LlamaIndex Document objects and write them to your vector store for semantic retrieval.

Yes, your FunctionAgent can call `get_docs_by_table` during a query run to inspect the structure of a specific table. This lets the agent decide how to format its final response based on the retrieved schema.

You use `get_versions` to fetch the active database versions and store this value in your node metadata. When a user queries LlamaIndex, the engine filters the vector store to match the requested database version.

Yes, the Vinkius MCP environment supports async execution for all 5 tools. You call `to_tool_list_async()` on your tool specification to run non-blocking taxonomic queries.

All communications with the FishBase MCP server go through a secure, single-point Vinkius gateway with zero-trust architecture. Your search queries and common name filters are processed in memory and wiped immediately after execution.

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