Compatible with every major AI agent and IDE
What is the BookStack (Wiki) MCP Server?
Connect your BookStack instance to any AI agent and turn your documentation into an interactive knowledge base through natural conversation.
What you can do
- Content Hierarchy — List and manage shelves, books, chapters, and pages using
list_shelves,list_books, andlist_pagesto maintain perfect organization. - Smart Search — Find exactly what you need across your entire wiki instance with the powerful
searchtool. - Full Content Lifecycle — Create, update, or delete pages and chapters directly from your agent to keep documentation fresh.
- Multi-format Export — Use
export_pageto retrieve content in PDF, Markdown, HTML, or Plaintext formats for external use. - System Oversight — Monitor your instance with
get_system_status, checklist_audit_logfor recent changes, or manage thelist_recycle_bin. - Attachments — Manage file attachments linked to your documentation using the dedicated attachment tools.
How it works
- Subscribe to this server
- Enter your BookStack URL, Token ID, and Token Secret
- Start managing your knowledge base from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Documentation Leads — maintain and organize large wikis without manual navigation
- Engineering Teams — search for technical specs and update READMEs directly from the IDE
- Support Teams — quickly find and export help articles for customers
Built-in capabilities (32)
Create a new attachment link
Create a new book
Create a new chapter
Requires either book_id or chapter_id, name, and html or markdown. Create a new page in BookStack
Create a new shelf
Delete an attachment
Delete a book
Delete a chapter
Delete a page (moves to recycle bin)
Delete a shelf
Export book content
Export chapter content
Export page content
Get details for a specific attachment
Get details for a specific book
Get details for a specific chapter
Get details for a specific page
Get details for a specific shelf
Check system version and status
List all attachments in BookStack
View system activity audit log
List all books in BookStack
List all chapters in BookStack
Supports pagination, sorting, and filtering. List all pages in BookStack
List deleted items in the recycle bin
List all shelves in BookStack
Search across all content in BookStack
Update an existing attachment
Update an existing book
Update an existing chapter
Update an existing page
Update an existing shelf
Why Vercel AI SDK?
The Vercel AI SDK gives every BookStack (Wiki) tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 32 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same BookStack (Wiki) integration everywhere
- —
Built-in streaming UI primitives let you display BookStack (Wiki) tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
BookStack (Wiki) in Vercel AI SDK
BookStack (Wiki) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect BookStack (Wiki) to Vercel AI SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for BookStack (Wiki) in Vercel AI SDK
The BookStack (Wiki) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 32 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Vercel AI SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
BookStack (Wiki) for Vercel AI SDK
Every tool call from Vercel AI SDK to the BookStack (Wiki) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
How does the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp
Explore More MCP Servers
View all →
BLS JOLTS — Job Openings, Quits & Turnover
2 toolsDeep-dive into the 'Great Resignation' and labor tightness with the US Job Openings and Labor Turnover Survey (JOLTS). Track hires, fires, and voluntary quits.

Tencent Docs
10 toolsCollaborative office workspace by Tencent — manage documents, sheets, and slides via AI.

Audienceful
10 toolsManage subscribers, custom fields, and email automations via Audienceful — orchestrate newsletters and campaigns directly via AI.

Confluent
7 toolsEnable your AI agent to manage Kafka clusters, topics, and environments via the Confluent Cloud API.
