BookStack (Wiki) MCP. Manage your entire knowledge base structure from your agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
BookStack (Wiki) MCP Server manages your knowledge base directly from your AI agent. Use this server to search, read, create, update, and delete pages, books, chapters, and shelves in your BookStack wiki.
You can also export content into PDF, Markdown, or HTML formats. This centralizes all your wiki operations, keeping your documentation clean and current.
What your AI agents can do
Create attachment
Creates a new link for an attachment file within BookStack.
Create book
Creates a new top-level book in the wiki structure.
Create chapter
Creates a new chapter that belongs inside an existing book.
Find specific pages or information across your entire wiki using the search tool.
Create and modify the basic organizational units—shelves, books, chapters, and pages—using dedicated creation and update tools.
Write, modify, or retire documentation using create_page, update_page, or delete_page.
Pull content out of the wiki in external formats like PDF, Markdown, or HTML using export_page, export_book, or export_chapter.
Check system status (get_system_status), view the activity log (list_audit_log), or manage attachments and the recycle bin.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019e386ecreate attachment
Creates a new link for an attachment file within BookStack.
019e386ecreate book
Creates a new top-level book in the wiki structure.
019e386ecreate chapter
Creates a new chapter that belongs inside an existing book.
019e386ecreate page
Creates a new content page, requiring specified book or chapter IDs, a name, and content in HTML or Markdown format.
019e386ecreate shelf
Creates a new organizational shelf within the wiki.
019e386edelete attachment
Deletes an attachment linked to a specific piece of content.
019e386edelete book
Deletes an entire book, removing all its contained chapters and pages.
019e386edelete chapter
Deletes a chapter, removing all its content and associated pages.
019e386edelete page
Deletes a page, moving it to the recycle bin instead of permanently removing it.
019e386edelete shelf
Deletes an organizational shelf.
019e386eexport book
Exports all content from a specified book into a single file.
019e386eexport chapter
Exports all content from a specified chapter into a single file.
019e386eexport page
Exports the content of a single page into a specified format (PDF, MD, HTML, TXT).
019e386eget attachment
Retrieves details for a specific attachment link.
019e386eget book
Gets all metadata and content details for a specific book.
019e386eget chapter
Gets all metadata and content details for a specific chapter.
019e386eget page
Gets all metadata and content details for a specific page.
019e386eget shelf
Gets all metadata and content details for a specific shelf.
019e386eget system status
Checks the current operational status and version of the BookStack instance.
019e386elist attachments
Lists all attachment links available across the entire BookStack wiki.
019e386elist audit log
Retrieves a chronological record of all system changes and user actions.
019e386elist books
Lists every book available in the BookStack wiki.
019e386elist chapters
Lists every chapter available within the wiki structure.
019e386elist pages
Lists all individual pages, supporting filtering and sorting.
019e386elist recycle bin
Shows all items that have been deleted and are waiting for permanent removal.
019e386elist shelves
Lists all organizational shelves in the BookStack wiki.
019e386esearch
Searches the full text and metadata across every piece of content in the wiki.
019e386eupdate attachment
Updates the details or link for an existing attachment.
019e386eupdate book
Modifies the metadata or content of an existing book.
019e386eupdate chapter
Modifies the metadata or content of an existing chapter.
019e386eupdate page
Modifies the content or metadata of an existing page.
019e386eupdate shelf
Modifies the metadata of an existing organizational shelf.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with BookStack (Wiki), then connect any of our 4,500+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,500+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
This BookStack Wiki MCP Server lets your AI agent manage your knowledge base directly. You can search, read, create, update, and delete pages, books, chapters, and shelves in your BookStack wiki. You'll also get content exported to PDF, Markdown, or HTML. This centralizes every wiki operation, keeping your documentation current and clean. Your AI client can use search to find text and metadata across every piece of content.
You can list all available books with list_books, chapters with list_chapters, pages with list_pages, and organizational shelves with list_shelves. To start building out the structure, you've got create_book for new top-level books, create_chapter for chapters inside existing books, and create_shelf for new organizational shelves. You can also modify the existing structure by running update_book or update_shelf.
You've got get_book to get all metadata and content details for a specific book, and you can use get_chapter or get_page to pull metadata and content details for a chapter or a page. To actually write content, you use create_page or update_page, specifying the book or chapter IDs, a name, and content in HTML or Markdown.
If you need to remove something, you can delete_page (it just moves it to the recycle bin), or delete_chapter or delete_book. You can delete a shelf with delete_shelf or an attachment with delete_attachment. For content that's done, you can export a single page using export_page into PDF, MD, HTML, or TXT, or you can export all content from a specified chapter with export_chapter or from a whole book using export_book.
You can also check what's been deleted by running list_recycle_bin, and you can see a chronological record of all system changes and user actions using list_audit_log. You've got tools for attachments, too; you can list them all with list_attachments, get details for one with get_attachment, and update them using update_attachment.
You can also create a new attachment link using create_attachment. Lastly, you can check the operational status and version of the BookStack instance with get_system_status.**
How BookStack (Wiki) MCP Works
- 1 Subscribe to the server and enter your BookStack URL, Token ID, and Token Secret.
- 2 Your AI client sends a request to the BookStack MCP Server, specifying the desired action (e.g., 'Create a new chapter titled X').
- 3 The server executes the corresponding internal BookStack API call, making the change and returning the resulting content or confirmation ID to your AI client.
The bottom line is, your AI client executes standard BookStack API calls through natural language conversation.
Who Is BookStack (Wiki) MCP For?
Documentation leads, technical writers, and engineering teams who spend too much time clicking through wikis. If your knowledge base is a messy collection of links and manual updates, this server lets you manage the content structure directly from your chat window.
Creates new documentation, ensuring every new page has the correct structure (book, chapter, shelf) and uses create_page and update_page without leaving the writing tool.
Maintains the overall wiki structure, using tools like list_books and create_shelf to keep the hierarchy organized and up-to-date.
Researches and retrieves specific help articles for customers, using the search tool to locate the right page, and then uses export_page to quickly generate a PDF for support tickets.
What Changes When You Connect
- Instantly find content across your entire wiki. Instead of clicking through five different folders, running
searchfinds the relevant page ID and content snippet immediately. - Maintain structural integrity without manual clicking. Use
create_chapterorcreate_bookto build out a perfect hierarchy, knowing the system tracks every new relationship. - Handle content changes safely. When you need to edit a page, use
update_page. If you need to retire it,delete_pagemoves it to the recycle bin, giving you a safety net. - Export content into any format. Don't just copy/paste. Use
export_pageto pull content into PDF, Markdown, or HTML, ready for external reports. - Get a full audit trail. Need to know who changed what and when?
list_audit_logshows you every action taken, keeping your documentation accountable. - Manage the full life cycle. From creating a new
shelfto retiring a wholebook, this server gives you granular control over every piece of content.
Real-World Use Cases
Onboarding a new engineering team
The new team needs all security policies. Instead of asking a doc lead for a list of links, they ask their agent to 'Find all documents related to security policy'. The agent runs search and compiles a list of relevant pages, which they can then export using export_page as a PDF for the kickoff meeting.
Updating a technical spec across multiple documents
A core API endpoint changes. Instead of manually logging into 15 different pages, the developer instructs their agent to 'Update the 'Authentication Flow' page (ID: 88) across all books, ensuring the new endpoint details are included.' The agent runs update_page repeatedly, saving hours of manual work.
Rebuilding a section of the wiki
The old 'Legacy Systems' book needs a complete overhaul. The user tells the agent to 'Archive the 'Legacy Systems' book and start a new one called 'Decommissioned Services'.' The agent runs delete_book and then create_book, ensuring the structure is clean and ready for new content.
Preparing content for external stakeholders
The support team needs to send a comprehensive guide to a client. They ask the agent to 'Export the 'Advanced Troubleshooting' chapter (ID: 12) and package it as a Markdown file'. The agent uses export_chapter and delivers the clean, ready-to-use file.
The Tradeoffs
Treating the wiki like a file system
The user tries to find a page by remembering a folder path, leading them to manually click through list_shelves -> list_books -> list_chapters to narrow down the location.
→
Use the search tool. It indexes the content, not just the metadata. Just tell your agent what you need—'What was the process for generating a Quarterly Report?'—and it finds the page directly, regardless of where it lives.
Manually fixing content drift
A book's title changes, but the associated chapter title is missed, leaving the documentation inconsistent and confusing.
→
Use the update_book and update_chapter tools. The agent can modify the metadata for both simultaneously, keeping the content structure aligned and consistent.
Ignoring content governance
Deleting a critical page without realizing it's linked to a major feature, potentially breaking workflows.
→
Always run list_audit_log first. It shows every change, every deletion, and who made it. This way, you know the impact of deleting a page before you run delete_page.
When It Fits, When It Doesn't
Use this server if your documentation management requires treating the wiki as a single, interconnected data source. If your goal is to build a content graph—where pages are linked to books, chapters, and shelves—this is the right tool. It gives your AI agent full CRUD control over the entire content lifecycle.
Don't use it if you just need to read a single, static article and don't need to modify the source. For that, a simple content API might suffice. But if you need to manage the structure (e.g., 'I need to create a whole new book and put three chapters inside it'), you need the granular control this server provides. The presence of tools like list_books, create_book, and update_shelf confirms it's a structural management tool, not just a reader.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 32 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Navigating a sprawling wiki shouldn't feel like a game of Russian roulette.
Today, finding a specific piece of information means clicking through multiple nested menus. You check the main dashboard, then click the 'Engineering' shelf, then the 'API Reference' book, then the 'Auth' chapter. If the path changes, you get lost. You end up copy-pasting links and asking colleagues, 'Where did you find that?'
With this MCP server, you just tell your agent what you need. You don't describe the path. You ask: 'What is the authentication flow for v3?' The agent runs `search`, finds the exact page, and gives you the content, bypassing the entire click-through nightmare.
BookStack (Wiki) MCP Server: Exporting content in one command
Manually compiling a report involves downloading the content from the 'Billing' book, then copying the 'Pricing' chapter, and finally exporting the 'Terms' page. You lose formatting, you lose context, and you spend twenty minutes fixing the final document.
The agent handles this automatically. You tell it to 'Export the Billing Book and the Pricing Chapter'. The server uses `export_book` and `export_chapter` to package everything perfectly into a single, clean, formatted PDF, ready to send.
Common Questions About BookStack (Wiki) MCP
How do I update a page using the `update_page` tool? +
You pass the existing page ID, the new content (Markdown or HTML), and optionally, updated metadata. The agent overwrites the old content with the new data.
Can I find content that's been deleted using `list_recycle_bin`? +
Yes, list_recycle_bin shows you all deleted items. You can then use the appropriate get_ or restore tools (depending on the backend) to retrieve the metadata, confirming the content still exists.
Which tool should I use to find general information across the entire wiki? +
Use the search tool. It indexes the full text of every page, book, and chapter, making it the most powerful and broadest search mechanism available.
What is the difference between `list_books` and `list_shelves`? +
list_books retrieves the major, top-level content containers. list_shelves lists secondary organizational grouping units that sit between the books and the actual content.
How do I manage attachments for a specific page using `get_attachment`? +
The get_attachment tool retrieves details for a specific attachment link. You'll need the attachment's ID to use it. This lets you confirm the link's existence and details before working with it.
If I need to update an entire book, which tool do I use: `update_book` or `update_page`? +
Use update_book to change details that apply to the whole book. If you only need to revise the text on a single page, update_page is the right choice.
What is the function of `list_audit_log` and what information does it provide? +
list_audit_log shows system activity records. It tracks who made changes and when, helping you monitor the entire wiki's history for compliance or debugging.
When exporting content, should I use `export_page` or `export_book`? +
Use export_page when you want a single piece of content exported. For a collection of content, like an entire book, export_book handles that scope.
Can I search across all my books and chapters at once? +
Yes! Use the search tool with your query string. It will return relevant results from pages, chapters, and books across your entire BookStack instance.
Is it possible to retrieve a page's content in Markdown format? +
Absolutely. Use the export_page tool and set the format to 'markdown'. You can also export to PDF, HTML, or plaintext.
How do I see what was recently deleted? +
You can use the list_recycle_bin tool to view items that have been moved to the recycle bin before they are permanently removed from the system.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Discord
Manage Discord servers, post messages, organize channels, and moderate communities with full bot-level API access.
Ideanote
Manage ideas, missions, and innovation workspaces via Ideanote API.
DingTalk
Alibaba's B2B office platform — manage users, departments, send notifications, track attendance, and automate approval workflows.
You might also like
GovInfo (GPO Legislative Docs)
Access official US government documents, legislative bills, and federal registers directly from the GPO.
Bollinger Bands Engine
Calculate moving standard deviation and Bollinger Bands for financial time-series deterministically.
PG&E Data Portals
Search and query PG&E energy datasets: usage, EV adoption, solar, grid data.