How to Use the Kavita (eBook/Manga) MCP in AutoGen

Q: How do I load Kavita (eBook/Manga) tools into AutoGen?

Install autogen-extmcp. Use mcpservertools with your endpoint URL, then pass the resulting list into your AssistantAgent constructor.

Deploy debating AutoGen agents to manage your Kavita server load and library scans.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kavita (eBook/Manga) MCP to AutoGen

Create your Vinkius account to connect Kavita (eBook/Manga) 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 Kavita (eBook/Manga) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Global Scans

The `scan_all_libraries` tool triggers a massive global update across your entire host. Because this operation spikes CPU, your AutoGen setup can feature a performance agent and a content agent debating the execution time. The content agent wants immediate updates, while the performance agent delays the tool call until off-peak hours to prevent streaming stutter.

AutoGen MCP Server Execution

The `scan_library` tool restricts the disk read operation to a single target folder. If the agents reach a consensus that a global scan is too expensive, they fall back to this targeted method. They extract the exact library ID from your prompt and update only the manga directory you just modified.

Shared Agent Authentication

The `authenticate` and `check_authkey_expires` tools provide the necessary credentials for the agents to interact with the API. One dedicated security agent monitors the session state. When the key nears expiration, it preempts the other agents, generates a fresh JWT, and updates the shared context so no tool calls fail due to a 401 error.

Setup guide

Set up Kavita (eBook/Manga) 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 Kavita (eBook/Manga) 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="Kavita (eBook/Manga)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kavita (eBook/Manga) 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="Kavita (eBook/Manga)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kavita (eBook/Manga) 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 Kavita. 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 Kavita (eBook/Manga) 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 Kavita (eBook/Manga) MCP in AutoGen

Install autogen-ext[mcp]. Use mcp_server_tools with your endpoint URL, then pass the resulting list into your AssistantAgent constructor.

Yes. You can define a system prompt where agents negotiate the timing. They evaluate server load and decide whether to call `scan_library` now or `scan_all_libraries` later.

The McpToolAdapter handles the schema conversion and execution. A single agent handles the `authenticate` call, and the resulting JWT persists in the shared conversation context for other agents to use.

Yes. The AutoGen implementation supports Streamable HTTP transports. You point the client at the provided endpoint and it pulls the tool definitions automatically.

Your library directory paths and authentication payloads remain strictly isolated. Vinkius provisions an ephemeral sandbox for the connection, ensuring no session states or API keys persist after the agents finish their debate.

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