How to Use the BookStack (Wiki) MCP in AutoGen

Q: Can one AutoGen agent read a page while another updates BookStack (Wiki)?

Yes. An agent can call getpage to read the content, share it in the chat thread, and another agent can call updatepage based on their discussion.

Q: Can AutoGen agents organize books into shelves in BookStack (Wiki)?

Yes. Your agents can use the MCP tools to call listbooks to find unorganized content, then use createshelf or updateshelf to group those books into the correct categories.

Deploy AutoGen multi-agent teams to collaborate, edit, and organize your BookStack (Wiki) documentation.

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 AutoGen

Create your Vinkius account to connect BookStack (Wiki) 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 BookStack (Wiki) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen Wiki Editorial Workflows

Set up an AutoGen writing team using this MCP Server where one agent drafts content with `create_page` and another reviews it. If edits are needed, the editor agent executes `update_page` with corrections. This collaborative loop happens autonomously in the background, ensuring your wiki articles meet style guides before publication.

Automated Wiki Structure Management

Let your agent team debate how to categorize documentation by letting a librarian agent call `list_shelves` and `list_books` to analyze your hierarchy. Once the agents agree on a structure, they execute the changes using `create_shelf` or `create_book`. This keeps your knowledge base orderly without requiring manual sorting from your engineering team.

Audit Log Monitoring and Alerts

Monitor your wiki for unexpected modifications by deploying a security agent that runs `list_audit_log` at regular intervals. If it detects an unauthorized edit, it can trigger a rollback by calling `update_page` with previous content. It can also move spam pages to the recycle bin using `delete_page` to protect your wiki's integrity.

Setup guide

Set up BookStack (Wiki) 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 BookStack (Wiki) 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="BookStack (Wiki)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent BookStack (Wiki) 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="BookStack (Wiki)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

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

You register the MCP Server tools with the assistant agents using the AutoGen MCP adapter. This gives your agents access to commands like `search` and `create_page` during their conversations.

Yes. An agent can call `get_page` to read the content, share it in the chat thread, and another agent can call `update_page` based on their discussion.

The Vinkius sandbox handles concurrent requests safely. If multiple agents attempt to call `update_book` or `create_chapter` at once, the server processes them reliably without conflicts.

Yes. Your agents can use the MCP tools to call `list_books` to find unorganized content, then use `create_shelf` or `update_shelf` to group those books into the correct categories.

Vinkius isolates your wiki shelves, chapters, and API keys in a zero-trust runtime environment. Your credentials never leak into the AutoGen LLM conversation context, and all tool execution happens via secure, single-use tokens.

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