How to Use the Kavita (eBook/Manga) MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK assistant trigger selective updates instead of global scans?

Yes, the scanlibrary tool accepts a specific library ID to target only your manga or eBook folder. This prevents CPU spikes on your hosting machine by avoiding the heavy global scan tool.

Q: Does the Kavita (eBook/Manga) server handle session timeouts automatically?

The agent uses checkauthkeyexpires to verify the active token before running any tasks. When the key is close to expiration, the agent calls authenticate to refresh the JWT token behind the scenes.

Expose your Kavita library directly to your OpenAI Agents SDK production deployment using this lightweight MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Kavita (eBook/Manga) 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 Kavita (eBook/Manga) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate library syncs via OpenAI Agents SDK

The `scan_library` and `scan_all_libraries` tools let your agent trigger targeted or global directory updates on your Kavita server. When new manga files land in your storage, your Python agent detects the change and immediately updates the database. You don't need to manually click scan in the web UI. This integration handles the API calls in the background, keeping your reading list current without lag.

Manage session health with built-in guardrails

The `authenticate` tool manages your JWT tokens while `check_authkey_expires` monitors the validity of your active sessions. Your agent checks token expiration before initiating heavy scans, avoiding unexpected connection drops. OpenAI's tracing dashboard tracks these security calls in real time. If a token expires, the agent negotiates a new session automatically without throwing silent errors.

Coordinate multi-agent file processing

This MCP Server enables specialized agents to hand off tasks when processing fresh media uploads. One agent handles file naming, while another calls `scan_library` to import the processed volume. Safety guardrails validate each payload before execution. Your Kavita server stays protected from accidental double-scans or rapid-fire API requests.

Setup guide

Set up Kavita (eBook/Manga) 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 Kavita (eBook/Manga) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kavita (eBook/Manga) 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="Kavita (eBook/Manga) Agent",
            instructions="You have access to Kavita (eBook/Manga) 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 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 OpenAI Agents SDK

Install the package, define the server streamable HTTP parameters with your endpoint, and register it in your Agent constructor. Setting the caching parameter to true ensures your agent discovers the scanning tools instantly without extra network roundtrips.

Yes, the `scan_library` tool accepts a specific library ID to target only your manga or eBook folder. This prevents CPU spikes on your hosting machine by avoiding the heavy global scan tool.

The agent uses `check_authkey_expires` to verify the active token before running any tasks. When the key is close to expiration, the agent calls `authenticate` to refresh the JWT token behind the scenes.

You set up custom guardrails within your agent configuration to throttle requests. This prevents the model from calling the global scan tool repeatedly during large bulk imports.

Your Kavita API keys and JWT session tokens never leave your local environment or your private Vinkius sandbox. This MCP Server processes all authentication calls inside an ephemeral, isolated container, keeping your media server credentials completely hidden from external models.

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