Kavita (eBook/Manga) MCP for AI. Automate your media archive maintenance with AI.

Q: How do I check if my Kavita key is about to expire using checkauthkeyexpires?

You prompt the agent with a request to use checkauthkeyexpires. It will return the precise date of expiration, letting you know how much time you have before needing to update your credentials.

Q: Should I use scanalllibraries or scanlibrary?

Use scanalllibraries when you need a comprehensive system audit. Use scanlibrary only when you know the update is confined to one specific collection ID; it's faster and more precise.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Kavita (eBook/Manga) MCP lets your AI agent manage large media libraries. It handles core maintenance tasks like running global scans for new manga chapters or checking API key expiration dates.

You authenticate sessions and maintain index health without ever touching the web UI.

What your AI can do

Check authkey expires

Checks the specific date when your API key will become invalid or expire.

Authenticate

Retrieves a JWT token after verifying credentials to establish an active, secure connection.

Scan all libraries

Initiates a full scan across every single library on the server for new content.

+ 1 more capabilities included

Scan entire content libraries

Triggering scans across all connected collections to detect new files and update metadata.

Index specific library sections

Running a targeted scan on one library ID when you know exactly where the updates are.

Verify API key validity

Checking the expiration date of your access keys to prevent service outages.

Establish secure sessions

Authenticating with the server and retrieving necessary tokens for reliable interaction.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Kavita (eBook/Manga) - 4 Tools

These tools give your agent direct control over the core maintenance functions of your media server, from authentication to full library scanning.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Kavita (eBook/Manga) on Vinkius

Check Authkey Expires

Checks the specific date when your API key will become invalid or expire.

Authenticate

Retrieves a JWT token after verifying credentials to establish an active, secure...

Scan All Libraries

Initiates a full scan across every single library on the server for new content.

Scan Library

Starts a focused scan job on one specific library ID, useful for troubleshooting.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Kavita (eBook/Manga) integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "kavita-ebookmanga": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Kavita (eBook/Manga) tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"kavita-ebookmanga": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Kavita (eBook/Manga), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 4 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

The Manual Process of Library Maintenance

Right. So, today you gotta log into the web UI every time something changes. You click around: 'Is my API key good? Let me check.' Then, if that passes, you have to manually trigger a full scan across all your collections just to see if the latest chapter got indexed. If you only care about one specific manga series, you still might end up triggering a global scan anyway.

With this MCP, it's different. You tell your agent what job needs doing—'Check my library status and run scans.' The whole process runs in the background using structured calls, giving you confirmation without ever opening the web interface. It just works.

The `scan_all_libraries` Tool

Before this MCP, running a full scan meant leaving your current task and navigating to a specific maintenance tab. You'd click the button, wait for it to process hundreds of files, and hope nothing broke in the interim.

Now, you simply ask your agent to execute `scan_all_libraries`. The command runs directly against the server backend via API, giving you instant feedback on status and completion without any manual clicks or context switching.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Managing a growing digital library—especially one filled with ongoing content like comics or manga—is usually tedious. You have to manually trigger full scans, check keys, and ensure everything is indexed correctly. This MCP connects your media server directly to your AI client, letting you automate all that overhead using natural conversation.

Instead of navigating the web interface, you just ask your agent to 'check for new content' or 'verify my API key status.' It handles library maintenance, session authentication, and monitoring through a simple chat command. Because it integrates with Vinkius, you can connect this media management layer into any workflow using Claude, Cursor, or any compatible client.

Your AI acts like a dedicated librarian that never sleeps.

Built · Hosted · Managed by Vinkius Kavita (eBook/Manga) - Manage Media Libraries with AI

Server ID 019e38b4-9cae-726f-8e23-ac649ba8a9ef

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Eliminate manual scanning. Instead of clicking 'Scan All' in the web UI, you can tell your agent to use scan_all_libraries, and it handles triggering the global library scan instantly.

Stay ahead of service outages. Use check_authkey_expires to confirm if your API key is about to expire before it causes a content indexing failure.

Target updates precisely. If only one specific collection needs checking, use scan_library with a defined ID instead of running a time-consuming full system scan.

Secure access starts here. Run the authenticate tool first; your agent gets the necessary JWT token to talk to the server securely and reliably.

Get immediate status updates. You don't have to guess if content was indexed. Your agent confirms success or flags potential issues after any operation.

See it in action

01 01

The weekly archive maintenance cycle

A DevOps engineer needs confirmation that the nightly manga ingest process worked. Instead of logging into the web UI and running multiple scans, they ask their agent to scan_all_libraries and then follow up by checking the API key status with check_authkey_expires. The agent reports on both success metrics in one chat.

02 02

Troubleshooting a single collection

A collector notices only their sci-fi library is missing new chapters. They don't want to scan everything, so they ask the agent to scan_library using only that specific ID. The agent runs the targeted scan and confirms if the issue was indexing or an API failure.

03 03

Pre-deployment readiness check

A developer needs to confirm their service access before deployment. They ask the agent to authenticate first, confirming they have a valid token. Then, they run check_authkey_expires to ensure the key is good for the next quarter.

04 04

Automating onboarding for new content

A user adds a massive batch of books overnight. They ask the agent to trigger a scan, and because they used authenticate beforehand, the agent knows how to talk to the server right away and reports when the entire process is complete.

The honest tradeoffs

Assuming everything works

Anti-pattern

The user runs a scan and assumes success. Later, the content fails to index because the API key expired last week.

The Fix

Don't just run scan_all_libraries. Always pre-check access validity by running check_authkey_expires first. If it looks close to expiring, refresh your credentials using authenticate.

Overloading the server

Anti-pattern

Running scan_all_libraries every five minutes just because a few new files show up.

The Fix

If you only need to check one specific, known problematic collection, use scan_library instead. This limits the scope and saves resources.

Ignoring authentication

Anti-pattern

Asking the agent to perform any action without first setting up the connection details.

The Fix

You must run authenticate before making calls for library maintenance or status checks. This gets your credentials set up and gives you a usable token.

When It Fits, When It Doesn't

Use this MCP if your primary need is automated, API-level management of existing media metadata—specifically triggering scans or verifying access tokens. You need to run scan_all_libraries or scan_library. Don't use it if you just want to view the library contents; that requires a different read-only tool. If your problem is merely viewing files, stick to file explorers. However, if your workflow involves making sure those viewed files are correctly indexed and accessible via an API call, this MCP provides the necessary control plane using tools like authenticate and check_authkey_expires. It's about infrastructure health checks, not just browsing.

Questions you might have

How do I check if my Kavita key is about to expire using `check_authkey_expires`? +

You prompt the agent with a request to use check_authkey_expires. It will return the precise date of expiration, letting you know how much time you have before needing to update your credentials.

Should I use `scan_all_libraries` or `scan_library`? +

Use scan_all_libraries when you need a comprehensive system audit. Use scan_library only when you know the update is confined to one specific collection ID; it's faster and more precise.

What must I do before running any commands with `authenticate`? +

You must first provide your server URL and API key during setup. The agent uses this information to execute the authenticate tool, which establishes a secure session token you need for subsequent actions.

Does the MCP help me with manga indexing? (Kavita) +

Yes. You can use the tools to trigger scans and verify API status, ensuring your latest chapters are correctly indexed and ready in your collection.

If I use the `authenticate` tool, how do I pass the resulting JWT token to subsequent actions? +

The agent provides a temporary JSON Web Token (JWT). You must capture this token and include it in the headers of every follow-up request—like running a scan or checking status—to maintain session access.

What happens if I run `scan_library` on an empty folder, and what error codes should I expect? +

It completes successfully. The system confirms that the specified library was scanned but found no new content. Look for a 'Scan Complete' message rather than an error code.

After triggering `scan_all_libraries`, how can I verify that all libraries were indexed and updated? +

The tool returns a job ID or status report detailing which libraries are processing. Wait for the final confirmation message before assuming indexing is complete; check the logs for any warnings.

Does `check_authkey_expires` only work with my primary Kavita instance, or can I monitor multiple locations? +

The tool queries a single configured API endpoint. To monitor multiple media sources, you'll need to configure and run the check against each distinct Kavita URL.

Can I trigger a scan for just one specific library? +

Yes! Use the scan_library tool and provide the specific Library ID. The agent will trigger a targeted scan to detect new or changed content in that folder only.

How do I check if my API key is still valid? +

You can run the check_authkey_expires tool. It will return the exact expiration timestamp for your current API key, helping you avoid service interruptions.

Can I refresh my entire collection at once? +

Absolutely. Use the scan_all_libraries tool to trigger a global scan across all configured libraries in your Kavita instance.

Connect to your AI in seconds.

Check authkey expires

Authenticate

Scan all libraries

Kavita (eBook/Manga) - 4 Tools

Make your AI actually useful.

Check Authkey Expires

Authenticate

Scan All Libraries

Scan Library

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

The Manual Process of Library Maintenance

The `scan_all_libraries` Tool

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

The weekly archive maintenance cycle

Troubleshooting a single collection

Pre-deployment readiness check

Automating onboarding for new content

The honest tradeoffs

Assuming everything works

Overloading the server

Ignoring authentication

When It Fits, When It Doesn't

Questions you might have