How to Use the Kitsu MCP in AutoGen

Q: How do I register Kitsu tools in an AutoGen agent?

Install the autogen-extmcp package and use mcpservertools with your server URL. Pass the generated tools list directly into your AssistantAgent constructor.

Q: How does AutoGen handle schema conversion for Kitsu tools?

The McpToolAdapter converts the MCP server's schemas into the format that AutoGen agents expect. You don't have to write any manual mapping code.

Build AutoGen multi-agent systems that debate and coordinate to manage your Kitsu watchlist and search manga.

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 AutoGen

Create your Vinkius account to connect Kitsu to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate for Kitsu watchlist management

AutoGen lets you set up multiple agents that talk to each other to manage your collection. For example, a curator agent can use `list_anime` to find new releases, while a critic agent reviews your watch history with `list_library_entries` to decide if you would actually enjoy them. Instead of relying on a single agent's guess, you get a collaborative decision. Once they agree on a title, a library agent can execute `create_library_entry` to add the show to your list.

Coordinate anime updates with this Kitsu MCP Server

When managing a shared or large watch list, mistakes happen. You can set up a security agent that monitors calls to `update_library_entry` and checks them against your current progress fetched by `get_current_user` before committing changes. This multi-agent verification prevents accidental deletions or rating changes. The agents work together to ensure your library updates are accurate and reflect what you have actually watched.

Automate manga research with AutoGen agents

You can assign specialized roles to different agents to gather deep insights on manga. One agent can run `list_manga` to find highly-rated series, while another uses `get_manga` to analyze the genres and themes. By dividing the labor, your agents can process large amounts of data quickly. They summarize their findings in a group chat, presenting you with a curated list of recommendations without cluttering your workspace.

Setup guide

Set up Kitsu MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kitsu tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kitsu_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kitsu data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kitsu_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kitsu data")
    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 AutoGen

Install the `autogen-ext[mcp]` package and use `mcp_server_tools` with your server URL. Pass the generated tools list directly into your `AssistantAgent` constructor.

Yes, any agent in your conversation group can access the registered tools. They can coordinate calls to `get_anime` and `list_library_entries` to share information during their debate.

The `McpToolAdapter` converts the MCP server's schemas into the format that AutoGen agents expect. You don't have to write any manual mapping code.

No, the server doesn't support changing profile settings. Agents can only fetch user details using `get_user` or `get_current_user`, and manage library entries.

Your library entries and user credentials are safe. Vinkius runs the server in an isolated V8 sandbox, and authentication tokens are managed securely on our end, keeping your private data hidden from the LLM conversation 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