How to Use the Calibre-Web MCP in CrewAI

Deploy a team of autonomous CrewAI agents to curate, organize, and sync your Calibre-Web library.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Calibre-Web MCP to CrewAI

Create your Vinkius account to connect Calibre-Web 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 Calibre-Web with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Library Curation

CrewAI excels at delegating specific tasks to specialized agents. You can assign a Researcher agent to map out your entire database using `get_opds_catalog`. It reads the XML feed, extracts the metadata, and builds a complete index in shared memory. Another agent then analyzes that index to find missing authors or duplicate entries. You pass the Vinkius endpoint URL directly into the array, giving your Python crew instant access to the database.

Autonomous Shelf Management via MCP Server

Managing reading lists manually takes hours. You can spin up a Librarian agent dedicated solely to organizing specific collections. It calls `get_opds_shelf` to audit current lists and determines what books belong where based on your prompt rules. If you want strict control over what the agent touches, you use the HTTP server class. The tool filter lets you expose only the shelf-reading tools to the Librarian while hiding the rest.

Sequential Device Synchronization

Pushing updates to e-readers should happen after the library is fully organized. A Device Manager agent takes over as the final step in your sequential execution pipeline. It triggers `sync_kobo_library` only after the Librarian finishes its audit. The agent handles the Kobo token authentication and monitors the sync status. Because the crew operates autonomously, your devices stay updated in the background without any human intervention.

Setup guide

Set up Calibre-Web 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 Calibre-Web tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Calibre-Web 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="Calibre-Web Analyst",
        goal="Access and analyze Calibre-Web data via MCP.",
        backstory="Expert analyst with direct Calibre-Web access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Calibre-Web 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 Calibre-Web. 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 Calibre-Web 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 Calibre-Web MCP in CrewAI

Install the framework with the tools extra. Pass your Vinkius URL directly into the agent configuration. The framework automatically discovers the OPDS and sync tools.

Yes, different agents can share the same connection. A researcher might read the main catalog while a separate device manager syncs your Kobo, all communicating through shared memory.

Use the HTTP server configuration class. Apply a tool filter to expose only the OPDS reading tools, completely hiding the Kobo sync operation from your agents.

Yes. A manager agent can evaluate your reading goals and delegate OPDS fetching tasks to subordinate agents. The manager reviews their findings before deciding to execute a device sync.

Your authentication tokens and reading metadata run through a zero-trust V8 isolate. Vinkius executes the tool request and wipes the ephemeral environment immediately. Your credentials are never stored.

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