Wiki.js
Model Context Protocol (MCP) server for Wiki.js GraphQL API integration. Provides AI models with secure access to Wiki.js functionality through MCP protocol.
What is Wiki.js?
Wiki.js is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server for wiki.js graphql api integration. provides ai models with secure access to wiki.js functionality through mcp protocol.
Model Context Protocol (MCP) server for Wiki.js GraphQL API integration. Provides AI models with secure access to Wiki.js functionality through MCP protocol.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol (MCP) server for Wiki.js GraphQL API
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx wikijsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Wiki.js
The Wiki.js MCP Server bridges AI assistants to your self-hosted Wiki.js instance via its GraphQL API, providing over a dozen tools for page management—search, create, update, publish, and delete pages—plus user and group management, so Claude can read and write your organization's wiki directly from a chat interface.
Prerequisites
- A running Wiki.js instance (v2.x) with GraphQL API enabled
- A Wiki.js API token with appropriate read/write permissions
- Node.js 18 or higher and npm
- Git to clone the repository
- Claude Desktop, Cursor, or another MCP-compatible client
Clone the repository and run setup
Clone the server and run the automated setup script, which installs dependencies, creates a .env file template, and builds the TypeScript source.
git clone https://github.com/heAdz0r/wikijs-mcp-server.git
cd wikijs-mcp-server
npm run setupGenerate a Wiki.js API token
Log into your Wiki.js admin panel, navigate to Administration > API, create a new API key with read and write permissions, and copy the token value.
Configure the .env file
Edit the .env file created by the setup script. Set your Wiki.js instance URL (without /graphql) and the API token you just created.
PORT=3200
WIKIJS_BASE_URL=https://wiki.yourcompany.com
WIKIJS_TOKEN=your-wikijs-api-token-hereStart the server
Start the MCP server in HTTP mode (recommended for most clients) or stdio mode for direct editor integration.
# HTTP mode (recommended)
npm start
# STDIO mode for editor integration
npm run server:stdio
# Development mode with hot reload
npm run devConfigure your MCP client
For Cursor, add to .cursor/mcp.json. For Claude Desktop, add to claude_desktop_config.json using the stdio command.
{
"mcpServers": {
"wikijs": {
"command": "node",
"args": ["/absolute/path/to/wikijs-mcp-server/dist/server-stdio.js"],
"env": {
"WIKIJS_BASE_URL": "https://wiki.yourcompany.com",
"WIKIJS_TOKEN": "your-wikijs-api-token-here"
}
}
}
}Wiki.js Examples
Client configuration
Claude Desktop config using stdio mode with environment variables for the Wiki.js connection.
{
"mcpServers": {
"wikijs": {
"command": "node",
"args": ["/Users/yourname/wikijs-mcp-server/dist/server-stdio.js"],
"env": {
"WIKIJS_BASE_URL": "https://wiki.yourcompany.com",
"WIKIJS_TOKEN": "eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9..."
}
}
}
}Prompts to try
Prompts that exercise page search, creation, and management via the Wiki.js GraphQL tools.
- "Search Wiki.js for pages about deployment procedures"
- "Create a new wiki page at path /guides/onboarding with the following content: ..."
- "List all unpublished draft pages in the wiki"
- "Update the page at /docs/api-reference to add a new authentication section"
- "Show me all users in the wiki and their roles"Troubleshooting Wiki.js
GraphQL API errors or 401 Unauthorized responses
Verify your WIKIJS_TOKEN is correct and has not expired. In Wiki.js admin, check that the API key has the necessary permissions (read pages, write pages, manage users). Tokens can be regenerated from Administration > API.
WIKIJS_BASE_URL should not include /graphql
Set WIKIJS_BASE_URL to the root URL of your Wiki.js instance (e.g., https://wiki.example.com), not to the GraphQL endpoint. The server appends /graphql automatically.
npm run setup fails with TypeScript compilation errors
Ensure you have Node.js 18 or higher. Run `node --version` to check. If needed, use nvm to switch: `nvm install 18 && nvm use 18`, then rerun npm run setup.
Frequently Asked Questions about Wiki.js
What is Wiki.js?
Wiki.js is a Model Context Protocol (MCP) server that model context protocol (mcp) server for wiki.js graphql api integration. provides ai models with secure access to wiki.js functionality through mcp protocol. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Wiki.js?
Follow the installation instructions on the Wiki.js GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Wiki.js?
Wiki.js works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Wiki.js free to use?
Yes, Wiki.js is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Wiki.js Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Wiki.js? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Wiki.js in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Wiki.js?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.