How to Use the Kitsu MCP in Pydantic AI

Q: How do I integrate Kitsu with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset array directly into your Pydantic AI agent constructor.

Q: Does Pydantic AI support Kitsu library modifications?

It handles modifications natively. Your agent can call updatelibraryentry to change watch progress. The strict typing ensures the agent sends the correct integer values for episode counts.

Q: What transport method should I use for this server?

Use the unified MCPToolset approach with a Streamable HTTP or SSE URL. The older MCPServerHTTP class is deprecated in newer Pydantic AI versions.

Connect the Kitsu MCP Server to Pydantic AI for type-safe anime discovery and strict library management.

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 Pydantic AI

Create your Vinkius account to connect Kitsu to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Anime Queries

The `get_anime` and `list_anime` tools query the Kitsu API for show metadata, returning structured JSON responses. Your agent searches by specific filters to narrow down the exact series. Pydantic AI enforces strict runtime validation on every response. If the Kitsu API returns an unexpected data type for an episode count, your agent fails loudly with a clear validation error rather than hallucinating a fix.

Kitsu MCP Server Watch Tracking

The `update_library_entry` and `create_library_entry` tools push state changes to a user's anime or manga list. The agent passes the required parameters to log new episodes or change a show's status. You build systems that care about correctness. Because Pydantic AI validates the tool inputs before the request even leaves your server, you never accidentally wipe out a user's watch history with malformed API calls.

User History Extraction

The `get_current_user` and `list_library_entries` tools fetch the authenticated account details and the complete array of saved media. Your agent reads this to establish the user's baseline preferences. You can switch between OpenAI, Anthropic, or local models without rewriting your tool logic. The framework guarantees the Kitsu data structures remain consistent regardless of which LLM processes the user's watch list.

Setup guide

Set up Kitsu MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kitsu-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kitsu tools.",
)

result = await agent.run("List recent Kitsu transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset array directly into your Pydantic AI agent constructor.

Yes. The framework automatically validates every piece of data returning from tools like `get_manga` against your defined Pydantic models. You get guaranteed structure.

It handles modifications natively. Your agent can call `update_library_entry` to change watch progress. The strict typing ensures the agent sends the correct integer values for episode counts.

Use the unified `MCPToolset` approach with a Streamable HTTP or SSE URL. The older `MCPServerHTTP` class is deprecated in newer Pydantic AI versions.

The system touches your Kitsu profile metadata, anime episode counts, and manga reading states. Vinkius manages the connection using ephemeral sandboxes. Your private watch habits are never logged or stored on our infrastructure.

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