How to Use the Wiki.js MCP in LangChain

Q: What if I need to delete an old Wiki.js page using LangChain?

You'd first run getpage or listpages so the agent confirms its existence, then call deletepage. The chain ensures you don't accidentally wipe out live data.

Q: How do I verify the current structure of Wiki.js pages in LangChain?

You simply call listpages. The result gives you a direct inventory, letting your agent build an accurate map of all available topics before attempting anything else.

Build multi-step documentation pipelines with LangChain.

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 LangChain

Create your Vinkius account to connect Wiki.js to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List and Search Wiki.js content

Start by seeing what's available. You can call `list_pages` to get a full directory of your wiki, or use `search_pages` if you know keywords. This output acts as the initial context for your agent chain. Once the list is back, your ReAct agent decides which specific pages are relevant before needing to execute any write operations.

Get detailed page content

The process needs detail. Use `get_page` when you find a path that looks promising. This tool pulls the full source text, letting your agent analyze the raw data—say, checking if an old procedure was deprecated. That output is critical because it determines whether you need to call `update_page` or just pass the information along to another API in your chain.

Create and modify pages

Need new documentation? Call `create_page` with the content. If the page exists but is wrong, don't create it—call `update_page`. This gives your agent control over the full lifecycle of the knowledge base. It’s a clean sequence: Search -> Get context -> Decide if write/update is needed.

Setup guide

Set up Wiki.js MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Wiki.js tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "wikijs-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Wiki.js transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

The agent doesn't just update; it chains the steps. For instance, it might `search_pages`, get a list, decide which page needs fixing, and then use `update_page`—all in one logical flow.

You'd first run `get_page` or `list_pages` so the agent confirms its existence, then call `delete_page`. The chain ensures you don't accidentally wipe out live data.

Yes. Because it handles tool calls as links in a chain, your agent can aggregate and reason across several different MCP Servers sequentially.

This MCP Server touches Wiki.js page content and paths. Your agent will deal with raw markdown/text strings when reading or writing documentation.

You simply call `list_pages`. The result gives you a direct inventory, letting your agent build an accurate map of all available topics before attempting anything else.

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