How to Use the Wiki.js MCP in Pydantic AI

Q: How do I search for content in Wiki.js using Pydantic AI?

Use the searchpages tool through your agent. Because of Pydantic validation, you get a predictable data structure back, confirming every field and type returned from Wiki.js.

Q: Can I create new pages for Wiki.js using Pydantic AI?

Yes, the createpage tool is available. When your agent calls it, the data passed must conform to defined schemas, ensuring robust record creation in Wiki.js.

Q: What happens if I update a page for Wiki.js using Pydantic AI?

The updatepage tool first runs the new content through validation. If the structure is wrong, the agent fails with an explicit error message; it never corrupts your Wiki.js data.

Q: Do I need to list all pages of Wiki.js using Pydantic AI?

If you need a full catalog, use listpages. The tool ensures the output is predictable and validated against expected models, making downstream processing reliable.

Type-safe documentation management with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wiki.js MCP to Pydantic AI

Create your Vinkius account to connect Wiki.js 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 Wiki.js with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage and edit Wiki pages reliably.

The `update_page` tool lets your agent modify existing content in Wiki.js, but it does so while validating the input structure against a Pydantic model. You never get silent errors. This means when you revise an article, the system confirms the data format is correct before sending it to Wiki.js.

Create new pages with guaranteed types.

When your agent uses `create_page`, Pydantic validates that all required fields—like title and content body—are present and the right type. The operation fails loudly if anything is off. This guardrail approach ensures every new page added to Wiki.js meets strict data standards.

List, search, or fetch pages safely.

Whether you use `list_pages` for an overview, `search_pages` for deep dives, or `get_page` to check a specific document, Pydantic validates the expected output structure. You know exactly what data format your agent is receiving. This validation protects against unexpected field names when interacting with Wiki.js.

Setup guide

Set up Wiki.js 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": {
        "wikijs-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Wiki.js 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 Wiki.js. 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 Wiki.js 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 Wiki.js MCP in Pydantic AI

Use the `search_pages` tool through your agent. Because of Pydantic validation, you get a predictable data structure back, confirming every field and type returned from Wiki.js.

Yes, the `create_page` tool is available. When your agent calls it, the data passed must conform to defined schemas, ensuring robust record creation in Wiki.js.

The `update_page` tool first runs the new content through validation. If the structure is wrong, the agent fails with an explicit error message; it never corrupts your Wiki.js data.

If you need a full catalog, use `list_pages`. The tool ensures the output is predictable and validated against expected models, making downstream processing reliable.

This server handles Wiki.js page content (text strings) and string paths (page identifiers). The core value here is enforcing type correctness on that returned data.

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