How to Use the Kitsu MCP in LangChain

Q: Can my LangChain agent update my watch status on Kitsu?

Yes, your agent can modify your list directly. It uses updatelibraryentry to change progress or ratings, and createlibraryentry to add new series.

Q: Can I search for both anime and manga in a single LangChain run?

Absolutely. The agent can call listanime and listmanga in parallel or sequentially within the same chain to gather full details for your queries.

Build LangChain agents that update your anime watchlist and search manga databases in multi-step reasoning chains.

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 LangChain

Create your Vinkius account to connect Kitsu to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step anime tracking chains with LangChain

Your LangChain agent can link multiple actions together to manage your watchlist. For example, it can run `list_anime` to find a trending show, check if it is already in your collection using `list_library_entries`, and then run `create_library_entry` to add it if missing. This turns simple API calls into a smart, automated pipeline. By feeding the output of one tool directly into the next, your agent handles complex watchlists without manual intervention. You get a single, fluent execution flow where the agent decides the best order of operations based on what it finds on Kitsu.

Monitor Kitsu MCP Server tools in LangSmith

Debugging agent decisions shouldn't feel like guesswork. When you connect this MCP server to your LangChain setup, every single call to `get_anime` or `update_library_entry` is tracked inside LangSmith. You see the exact latency, token count, and raw JSON payloads passing between your agent and the Kitsu API. This deep visibility helps you catch failed library updates or slow searches before they affect your users. You can inspect how the agent interprets Kitsu data and tweak your prompts to make tool selection more reliable.

Combine manga search with vector databases

LangChain lets you mix these anime tools with its massive ecosystem of over 500 integrations. Your agent can search for a series using `list_manga`, pull the description with `get_manga`, and instantly write that data to a local vector store or post a summary to a Discord channel. You aren't locked into a single API or platform. This flexibility allows your agent to cross-reference Kitsu library entries with external databases to build a personalized recommendation engine.

Setup guide

Set up Kitsu MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kitsu tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kitsu-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kitsu transactions"
    })
    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 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 LangChain

Install the adapter package and initialize the client using `MultiServerMCPClient`. Call `get_tools()` to retrieve the Kitsu functions, then pass them directly into your `create_agent` call.

Yes, your agent can modify your list directly. It uses `update_library_entry` to change progress or ratings, and `create_library_entry` to add new series.

The server is stateless by default to keep things fast. If you need to maintain a persistent connection for a specific user, use `client.session()` to keep the context active across multiple chain steps.

Absolutely. The agent can call `list_anime` and `list_manga` in parallel or sequentially within the same chain to gather full details for your queries.

Your Kitsu credentials and library data are processed locally within your sandboxed runtime. Vinkius handles the underlying authentication token securely, ensuring your raw login details are never exposed to the LLM or external logs.

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