How to Use the Kitsu MCP in LlamaIndex

Q: How do I connect the Kitsu MCP Server to LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient with your server URL. Wrap it in a McpToolSpec and pass the tools to your FunctionAgent.

Q: Can LlamaIndex index my entire Kitsu manga library?

Yes, your agent can call listlibraryentries to fetch your manga list and load those records directly into a vector store. This lets you perform semantic queries over your collection.

Q: Is it possible to search Kitsu categories using LlamaIndex?

Yes, your agent can use listanime with specific category filters to find matches. The returned data can then be indexed on the fly for immediate search retrieval.

Index your Kitsu watchlist into LlamaIndex vector stores to build semantic search engines for your anime collection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kitsu MCP to LlamaIndex

Create your Vinkius account to connect Kitsu 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 Kitsu with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Kitsu data for semantic search

LlamaIndex doesn't just execute API calls; it indexes the results directly into your knowledge base. When your agent runs `list_library_entries`, the output is saved to a vector store so you can query your watch history using natural language. This stops your agent from making repetitive API calls to check what you've watched. Instead, it searches the indexed Kitsu data locally, giving you instant answers grounded in your actual library.

Build anime RAG apps using this Kitsu MCP Server

You can combine live Kitsu details with local documents to build a highly contextual anime companion. Use `get_anime` or `get_manga` to pull specific metadata, then merge it with fan-written reviews or wiki articles inside a unified LlamaIndex query engine. This setup ensures your agent has access to both official database records and external text files. The agent can answer complex questions about plot points or character arcs while keeping track of your personal library progress.

Control agent tool access with LlamaIndex filters

Sometimes you want to restrict what an agent can do with your account. You can use the `allowed_tools` filter in LlamaIndex to let your agent call `list_anime` and `get_manga` for research, while blocking write tools like `update_library_entry`. This provides a safe way to build public-facing search tools. You get the benefits of Kitsu's database without risking accidental modifications to your personal library lists.

Setup guide

Set up Kitsu 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 Kitsu 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 Kitsu tools.",
)
response = await agent.run("List recent Kitsu 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 Kitsu. 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 Kitsu 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 Kitsu MCP in LlamaIndex

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient` with your server URL. Wrap it in a `McpToolSpec` and pass the tools to your `FunctionAgent`.

Yes, your agent can call `list_library_entries` to fetch your manga list and load those records directly into a vector store. This lets you perform semantic queries over your collection.

The framework manages tool execution sequentially to avoid hitting API rate limits. You can also filter tools so the agent only fetches necessary data using `get_anime` or `get_manga` rather than pulling your entire history repeatedly.

Yes, your agent can use `list_anime` with specific category filters to find matches. The returned data can then be indexed on the fly for immediate search retrieval.

Your library entries and user profile details are processed inside a secure V8 sandbox. Authentication tokens are handled securely on the server side, keeping your credentials isolated from the LLM context.

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