How to Use the BookStack (Wiki) MCP in Pydantic AI

Q: How do I set up BookStack (Wiki) with Pydantic AI?

Install the slim MCP package and use MCPToolset with your Vinkius server URL. Pass this toolset directly into your Agent constructor.

Q: What happens if BookStack (Wiki) returns bad data to Pydantic AI?

The framework validates the response from tools like getbook or search against its internal models and raises a validation error instantly.

Q: Can Pydantic AI create books and chapters in BookStack (Wiki)?

Yes. Your agent can use createbook and createchapter while enforcing strict input validation on titles and descriptions.

Run type-safe operations on your BookStack (Wiki) with Pydantic AI to guarantee structured data validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BookStack (Wiki) MCP to Pydantic AI

Create your Vinkius account to connect BookStack (Wiki) to Pydantic 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 BookStack (Wiki) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe wiki operations with this MCP Server

The `get_page` tool fetches wiki content and validates the returned JSON structure against strict Pydantic schemas at runtime. This prevents your agent from processing malformed HTML or missing page attributes. If your BookStack API returns unexpected data, this MCP Server setup causes the agent to fail loudly and immediately. You get clean, predictable behavior without worrying about silent failures during automated updates.

Strict page and shelf creation

The `create_page` tool requires specific parameters like book ID, chapter ID, name, and content format. Pydantic AI validates these arguments before the tool call ever leaves your local environment. You can build reliable automation scripts that handle `create_shelf`, `create_book`, and `create_chapter`. The framework ensures every created asset matches your corporate schema perfectly.

Reliable attachment and audit logging

The `list_attachments` and `list_audit_log` tools return structured lists that your agent can parse with complete type safety. This makes it easy to filter attachments by size, type, or parent page. If you need to update assets, `update_attachment` ensures that the modified metadata conforms to your application's data models before committing changes to the wiki.

Setup guide

Set up BookStack (Wiki) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "bookstack-wiki-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to BookStack (Wiki) tools.",
)

result = await agent.run("List recent BookStack (Wiki) transactions")
print(result.output)

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 BookStack. 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 BookStack (Wiki) 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 BookStack (Wiki) MCP in Pydantic AI

Install the slim MCP package and use `MCPToolset` with your Vinkius server URL. Pass this toolset directly into your Agent constructor.

The framework validates the response from tools like `get_book` or `search` against its internal models and raises a validation error instantly.

Yes. Your agent can use `create_book` and `create_chapter` while enforcing strict input validation on titles and descriptions.

You can. Pydantic AI is model-agnostic, meaning you can run these wiki tools using local LLMs or any commercial API provider.

Every MCP request containing your books, pages, or attachments runs in an isolated, ephemeral V8 container. No persistent storage is used, keeping your internal documentation completely private.

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