How to Use the Wiki.js MCP in AutoGen

Q: Can AutoGen plan a full site audit of Wiki.js?

Yes. Agents can use listpages to get an inventory, then systematically call getpage for every item, gathering all necessary data points into a single discussion.

Achieve consensus on Wiki.js documentation changes with AutoGen.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate the best search strategy

When facing a knowledge gap, multiple agents can debate how to proceed. One agent might suggest using `search_pages`, while another argues that running `list_pages` first will provide better context for deliberation. This consensus-driven approach prevents blind calls and ensures the right tool is picked.

Review and correct documentation

Imagine one agent finding conflicting information, flagging it as a risk. A second agent then proposes calling `update_page` to fix the discrepancy, leading to a final agreed-upon action. This negotiation capability is key for complex content governance in Wiki.js.

Plan site restructuring

The agents can collaboratively decide which pages are outdated and need removal. They might start by calling `list_pages` to inventory the entire system, followed by a debate over whether certain sections should be deleted via `delete_page`. It's about achieving group agreement on maintenance tasks.

Setup guide

Set up Wiki.js MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Wiki.js tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Wiki.js_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Wiki.js data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Wiki.js_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Wiki.js data")
    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 AutoGen

Agents debate the content first. The system doesn't just run `update_page`; it simulates consensus on *what* needs to change before committing the final action.

Yes. Agents can use `list_pages` to get an inventory, then systematically call `get_page` for every item, gathering all necessary data points into a single discussion.

The agents can first research the topic via searching or reading existing pages, debate the required structure, and then converge on calling `create_page` with finalized content.

This MCP Server exposes Wiki.js page content and paths. The agents handle this as raw markdown/text strings during their deliberations.

The multi-agent setup forces different perspectives on the search query, ensuring that potential results are vetted by multiple 'experts' before any conclusion is drawn.

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