BookStack MCP Server
Provides tools for searching pages within a BookStack instance, retrieving structured data such as titles, URLs, and content with clean HTML-to-text conversion.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BookStack MCP Serversearch for the company onboarding guide"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BookStack MCP Server
A Model Context Protocol (MCP) server that provides tools for searching pages from BookStack. This server interacts with the BookStack API and provides structured data for pages with clean HTML-to-text conversion.
Features
Search pages from BookStack with customizable queries
Get structured data including titles, URLs, and content
Configurable pagination (page number and count)
HTML-to-text conversion for clean content reading
Clean error handling and validation
Related MCP server: BookStack MCP Server
Installation
Installing via Smithery
To install mcp-bookstack for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @yellowgg2/mcp-bookstack --client claudeInstalling Manually
Clone the repository:
git clone https://github.com/yellowgg2/mcp-bookstack.git
cd mcp-bookstackInstall dependencies:
npm installConfigure your environment:
Create a .env file with your BookStack API credentials or provide them in the MCP settings configuration file:
BOOKSTACK_API_TOKEN=your_token
BOOKSTACK_API_URL=your_bookstack_url
BOOKSTACK_API_KEY=your_api_keyBuild the server:
npm run buildAdd to your MCP settings configuration file (location depends on your system):
For VSCode Claude extension:
{
"mcpServers": {
"bookstack": {
"command": "node",
"args": ["/path/to/mcp-bookstack/build/app.js"],
"env": {
"BOOKSTACK_API_URL": "your_bookstack_url",
"BOOKSTACK_API_TOKEN": "your_token",
"BOOKSTACK_API_KEY": "your_api_key"
}
}
}
}Usage
The server provides a tool called search_pages that can be used to search pages from BookStack.
Tool: search_pages
Parameters:
query(string): Query to search for pagesDefault: "" (empty string)
page(number): Page number to returnRange: 1-10
Default: 1
count(number): Number of pages to returnRange: 1-30
Default: 10
Example usage:
use_mcp_tool with:
server_name: "bookstack"
tool_name: "search_pages"
arguments: {
"query": "knowledge base",
"page": 1,
"count": 5
}Sample output:
# Page Title
Page content in plain text format...
Source: https://your-bookstack-url/page-urlIntegrating with Claude
To use this MCP server with Claude, you'll need to:
Have the Claude desktop app or VSCode Claude extension installed
Configure the MCP server in your settings
Use Claude's natural language interface to interact with BookStack
Configuration
For the Claude desktop app, VSCode Claude extension, and Cursor, add the server configuration to:
// ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
// %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"bookstack": {
"command": "node",
"args": ["/path/to/mcp-bookstack/build/app.js"],
"env": {
"BOOKSTACK_API_URL": "your_bookstack_url",
"BOOKSTACK_API_TOKEN": "your_token",
"BOOKSTACK_API_KEY": "your_api_key"
}
}
}
}Example Interactions
Once configured, you can interact with Claude using natural language to search BookStack pages. Examples:
"Search for documentation about API usage in our BookStack knowledge base"
"Find information about deployment in our internal docs"
"Look up security guidelines in BookStack"
Claude will automatically use the appropriate parameters to search for the pages you want.
Page Response Structure
Each page response includes:
Title of the page
Full content of the page (converted from HTML to plain text)
Source URL to the original page
The HTML-to-text conversion handles:
HTML entity decoding
Line breaks and paragraph formatting
List items with bullet points
Removal of HTML tags
Whitespace normalization
Development
The server is built using:
TypeScript
Model Context Protocol SDK
Axios for API requests
Zod for data validation
dotenv for environment configuration
To modify the server:
Make changes to
src/app.tsRebuild:
npm run buildError Handling
The server includes robust error handling for:
API connection failures
Authentication issues
Invalid parameter values
Data parsing errors
Errors are returned with appropriate error codes and descriptive messages.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - feel free to use this in your own projects.
Available Tools
1 toolsearch_pagesC
Search pages from Bookstack
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number to return | |
| count | No | Number of pages to return (max 30) | |
| query | No | Query to search for pages |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description fails to disclose behavioral traits such as how the search is performed, limits, or effects. The agent is left guessing about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (3 words), which is efficient. However, it may be overly brief at the cost of completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is too minimal to guide an agent effectively. It does not specify return format or search behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what's in the schema, but the schema already explains the parameters well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'pages from Bookstack', indicating the tool's purpose. However, it could be more specific about the search type (e.g., full-text, metadata) to distinguish it from potential future search tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool or any exclusions or alternatives. The description lacks context about appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v1.0.0- First observed
search_pages
TDQS
With only one tool, there is no ambiguity between tools.
The single tool 'search_pages' follows a clear verb_noun pattern.
A BookStack server with only a search tool is severely under-scoped; typical usage requires CRUD operations on books, chapters, and pages.
The tool set lacks any creation, retrieval, update, or deletion capabilities, making it incomplete for the domain.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
Search your knowledge bases from any AI assistant using hybrid RAG.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Search and retrieve permission-aware knowledge from connected sources through Remly.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables interaction with BookStack knowledge management systems through the BookStack API. Supports searching, reading, creating, and updating documentation content with secure authentication and dual transport modes for flexible deployment.1724131MIT
- AlicenseBqualityDmaintenanceEnables AI models to interact with BookStack wiki instances through a comprehensive API interface. Supports content management (books, chapters, pages), user administration, search functionality, and content export in multiple formats.4117MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage BookStack documentation through natural language, supporting content browsing, search, and CRUD operations for books, chapters, and pages.-
- AlicenseBqualityAmaintenanceConnects BookStack knowledge bases to Claude through 47+ tools covering complete CRUD operations for books, pages, chapters, shelves, users, search, attachments, and permissions. Enables full management of BookStack content and configuration through natural language.5641384MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yellowgg2/mcp-bookstack'
If you have feedback or need assistance with the MCP directory API, please join our Discord server