How to Use the Kitsu MCP in OpenAI Agents SDK

Q: How do I connect the Kitsu MCP Server to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint URL. Pass it into your agent constructor using the mcpservers array.

Q: Can my OpenAI Agents SDK bot update a Kitsu library?

Yes, it can. The agent uses createlibraryentry to add new shows and updatelibraryentry to change watch progress. You just need to provide the correct authentication token.

Q: Does the agent know what anime I already watched?

It does if you tell it to check. The agent calls listlibraryentries to pull your current watch list. From there, it filters out shows you already completed.

Connect the Kitsu MCP Server to the OpenAI Agents SDK to build production-grade anime discovery and library management pipelines.

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 OpenAI Agents SDK

Create your Vinkius account to connect Kitsu to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Kitsu MCP Server Search Tools

The `list_anime` and `list_manga` tools let your OpenAI agent query the Kitsu database using text filters, season, year, or categories. You pass a search string, and the agent pulls back the matching titles. Since you build with the OpenAI Agents SDK, you can wrap these queries in strict guardrails. If a user asks a specialized anime discovery agent for 90s mecha recommendations, the agent queries the API and hands off the results to a separate library-management agent without breaking the chain.

Modify Library Entries

The `create_library_entry` and `update_library_entry` tools give your agent write access to a user's Kitsu watch list. It takes the specific anime or manga ID and changes the status, episode count, or rating. This means your deployed agent actually maintains state for the user. Instead of just answering questions, the system logs their progress in real time. You track every API call in the OpenAI dashboard to ensure the agent only executes the exact MCP tool updates the user requested.

Read User Context

The `get_current_user` and `list_library_entries` tools pull the authenticated user's profile and existing watch history. Your agent reads this data to understand what the user already watched before making recommendations. You don't want a bot suggesting Cowboy Bebop to someone who rated it ten years ago. By pulling the current library state first, the agent grounds its responses in actual user data.

Setup guide

Set up Kitsu MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kitsu tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kitsu tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kitsu tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kitsu Agent",
            instructions="You have access to Kitsu tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius endpoint URL. Pass it into your agent constructor using the `mcp_servers` array.

Yes, it can. The agent uses `create_library_entry` to add new shows and `update_library_entry` to change watch progress. You just need to provide the correct authentication token.

It does if you tell it to check. The agent calls `list_library_entries` to pull your current watch list. From there, it filters out shows you already completed.

You define strict rules for when the agent can call write operations like `update_library_entry`. The framework validates the agent's intent before executing the MCP tool.

The server only accesses your Kitsu user ID, profile details, and library entries. Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox. Your watch data passes through memory and disappears the second the session ends.

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