How to Use the Kitsu MCP in CrewAI

Q: How do I connect the Kitsu MCP server to a CrewAI agent?

Install the required dependencies using pip install crewaitools. Pass the server URL directly into the mcps array when defining your agent.

Q: Can CrewAI agents collaborate on my Kitsu watchlist?

Yes. One agent searches the database with listmanga, while a separate manager agent updates your profile via updatelibraryentry.

Q: Is it possible to restrict which Kitsu MCP tools a CrewAI agent uses?

Use MCPServerHTTP combined with toolfilter. This lets you limit a specific agent to safe read-only operations like getanime.

Deploy specialized CrewAI agents to manage your Kitsu library, research new anime, and track manga automatically.

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 CrewAI

Create your Vinkius account to connect Kitsu to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Anime Research Agents

Assign a dedicated researcher agent to scour genres using `list_anime` and `get_anime`. It builds a curated list of recommendations based on highly specific prompts. This agent ignores the noise and focuses purely on discovery. It compiles its findings and passes a structured report to the next agent in your CrewAI sequence.

CrewAI Manga Library Managers

A secondary execution agent takes those recommendations and modifies your actual reading list. It runs `create_library_entry` or `update_library_entry` without you lifting a finger. You define the roles, and the agents execute the work. The system handles the transition from finding a new manga via `list_manga` to actually tracking it on your profile.

Multi-Agent Profile Monitoring via MCP

Have a dedicated monitor agent track your reading habits in the background. It calls `list_library_entries` and `get_current_user` to analyze what genres you consume most frequently. The monitor feeds this context back to the researcher agent. This creates a self-improving loop where the CrewAI setup learns your tastes and refines its future searches automatically.

Setup guide

Set up Kitsu MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kitsu tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kitsu Analyst",
    goal="Access and analyze Kitsu data via MCP.",
    backstory="Expert analyst with direct Kitsu access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kitsu transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Kitsu Analyst",
        goal="Access and analyze Kitsu data via MCP.",
        backstory="Expert analyst with direct Kitsu access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kitsu transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Install the required dependencies using `pip install crewai[tools]`. Pass the server URL directly into the `mcps` array when defining your agent.

Yes. One agent searches the database with `list_manga`, while a separate manager agent updates your profile via `update_library_entry`.

Use `MCPServerHTTP` combined with `tool_filter`. This lets you limit a specific agent to safe read-only operations like `get_anime`.

They operate autonomously based on their initial instructions. You only step in if you configure a specific moderator agent to require approval.

Agents read your exact manga volume progress and anime episode ratings. Vinkius secures this connection through ephemeral, single-use auth tokens that expire the second the MCP Server completes the task.

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