How to Use the BookStack (Wiki) MCP in LlamaIndex

Q: How does LlamaIndex index my BookStack (Wiki) content?

The framework uses the MCP tool spec to pull data via exportbook or getpage. It then parses the HTML into document nodes, embeds them, and stores them in your vector database.

Q: Can I filter searches to specific shelves in BookStack (Wiki) using LlamaIndex?

Yes. You can configure your agent to call getshelf first to find the relevant book IDs, then restrict the vector search or document ingestion to those specific books.

Q: Does this MCP Server support indexing attachments?

Yes. Your agent can run listattachments and getattachment to locate uploaded files. You can then use LlamaIndex's file readers to parse and index those documents.

Build RAG pipelines that index your BookStack (Wiki) pages and chapters directly into LlamaIndex vector stores.

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 LlamaIndex

Create your Vinkius account to connect BookStack (Wiki) to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search Over Wiki Books with LlamaIndex

This MCP Server lets LlamaIndex ingest your entire knowledge base into a queryable vector index using `list_books` and `export_book`. Instead of basic keyword matching, your agent uses semantic search to locate hard-to-find answers. When a user asks a question, the index maps the query directly to the relevant wiki chapters retrieved via `get_chapter`.

Automated Wiki Content Ingestion

Keep your RAG application synchronized by letting your LlamaIndex pipeline use `list_audit_log` to discover which pages changed recently. For modified items, the pipeline runs `get_page` to grab the fresh HTML or markdown. It updates only those specific vectors in your database, saving token costs and keeping search results accurate.

Dynamic Knowledge Base Maintenance

Let your LlamaIndex agent clean up your internal documentation by calling `create_page` when user queries reveal gaps in your knowledge base. The agent can also clean up outdated or redundant content. It identifies duplicates during indexing and uses `delete_page` to move old drafts to the recycle bin, keeping your documentation clean.

Setup guide

Set up BookStack (Wiki) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all BookStack (Wiki) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to BookStack (Wiki) tools.",
)
response = await agent.run("List recent BookStack (Wiki) data")

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 LlamaIndex

The framework uses the MCP tool spec to pull data via `export_book` or `get_page`. It then parses the HTML into document nodes, embeds them, and stores them in your vector database.

Yes. You can configure your agent to call `get_shelf` first to find the relevant book IDs, then restrict the vector search or document ingestion to those specific books.

Yes. Your agent can run `list_attachments` and `get_attachment` to locate uploaded files. You can then use LlamaIndex's file readers to parse and index those documents.

You can set up a script using our MCP interface that queries `list_audit_log` to find recent changes. Your pipeline then updates only the modified pages using `get_page`, keeping your vector index fresh.

Yes. Your wiki pages, books, and audit logs are processed purely in-memory within an ephemeral V8 sandbox. No raw text is cached or written to persistent storage, and your API keys are protected using hardware-level encryption keys.

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