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

Q: Can LangChain schedule Kavita (eBook/Manga) scans?

Yes. You write a chron-triggered script that invokes the scanalllibraries tool. The agent handles the authentication automatically before firing the global refresh.

Q: Does the agent need a static API key?

No. It uses the authenticate tool to pull fresh JWT tokens dynamically. You just provide the initial credentials.

Build automated manga library management pipelines with LangChain and this dedicated 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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Session Lifecycle Control

The `authenticate` and `check_authkey_expires` tools give your LangChain agents direct control over Kavita session lifecycles. You string these into a ReAct agent loop. Before triggering any heavy disk operations, the agent checks the token. If it fails, it grabs a new JWT, logs the latency in LangSmith, and proceeds without dropping the chain.

LangChain MCP Server Integration

The `scan_library` tool lets your agent update specific manga folders without locking up the entire host database. You wire a webhook from your download client straight into a LangChain run. The agent parses the incoming payload, extracts the library ID, and executes the targeted scan.

Global Metadata Refreshes

The `scan_all_libraries` tool forces a global metadata refresh across your entire Kavita instance. Since this spikes CPU and disk I/O, you build a scheduled chain that runs exclusively at 3 AM. The agent triggers the MCP Server, waits for the completion signal, and outputs the final execution time to your admin dashboard.

Setup guide

Set up Kavita (eBook/Manga) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kavita (eBook/Manga) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kavita-ebookmanga-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kavita (eBook/Manga) transactions"
    })
    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 LangChain

Run pip install langchain-mcp-adapters langgraph. Pass the MCP Server URL to MultiServerMCPClient, grab the tools, and feed them into your create_agent setup.

Yes. You write a chron-triggered script that invokes the `scan_all_libraries` tool. The agent handles the authentication automatically before firing the global refresh.

Observability and error handling. If a scan fails, LangSmith logs the exact tool input and output. The agent can also retry or fallback to a targeted scan if the global one times out.

No. It uses the `authenticate` tool to pull fresh JWT tokens dynamically. You just provide the initial credentials.

The MCP protocol keeps your library paths and JWT tokens confined to your local environment. Vinkius runs the server in a V8 Isolate Sandbox, meaning your API keys are ephemeral and wiped 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