How to Use the Kitsu MCP in Mastra AI

Q: How do I install the Kitsu MCP server in Mastra AI?

Install the package with npm install @mastra/mcp@latest. Instantiate a new MCPClient with your endpoint URL and spread the results from listTools() into your agent.

Q: Do I need human approval for Kitsu library changes in Mastra AI?

You control execution permissions. Set requireToolApproval to true if you want a human to verify createlibraryentry actions before they commit.

Build resilient anime tracking workflows with Mastra AI and the Kitsu 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 Kitsu MCP to Mastra AI

Create your Vinkius account to connect Kitsu to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Watchlist Syncing

Mastra AI workflows excel at handling messy external triggers with this MCP integration. You can configure a pipeline that listens for new episode releases and calls `create_library_entry` to keep Kitsu updated automatically. Network failures happen, especially with third-party APIs. Mastra catches timeouts on `update_library_entry` and retries the request using exponential backoff. Your library stays accurate without manual intervention.

Conditional Manga Discovery

Chain `list_manga` to find new releases based on specific genre filters. The workflow takes that raw JSON and passes it through a decision tree. If a title meets the user's criteria, the agent pushes it to their reading list. You construct this entire logic flow in TypeScript, letting the MCP Server handle the actual data fetching via `get_manga`.

Reliable Kitsu Polling

Set up a background job to run `list_library_entries` on a cron schedule. The agent compares the current list against airing shows to generate weekly digest alerts. Verifying profile states happens through `get_user`. The workflow checks if the account is active before attempting any heavy data synchronization, saving API calls and reducing failure rates.

Setup guide

Set up Kitsu MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Kitsu tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "kitsu-mcp-client",
  servers: {
    "kitsu-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Kitsu Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Kitsu tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Kitsu transactions"
);
console.log(result.text);

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 Mastra AI

Install the package with `npm install @mastra/mcp@latest`. Instantiate a new `MCPClient` with your endpoint URL and spread the results from `listTools()` into your agent.

Built-in exponential backoff handles timeouts automatically. If a call to `update_library_entry` drops, the workflow tries again based on your configuration.

You control execution permissions. Set `requireToolApproval` to true if you want a human to verify `create_library_entry` actions before they commit.

It provides 9 distinct operations. These range from simple searches like `get_anime` to state mutations like updating watch progress.

The server processes user IDs, reading progress, and watch statuses. Vinkius enforces a strict zero-trust architecture, meaning no persistent storage exists and endpoints disappear immediately after the workflow finishes.

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