What is Wikijs Mcp and what does it do?
It is an MCP server that enables AI assistants to search and retrieve content from a WikiJS instance via four tools: search by query, get by ID, get by path/locale, and list all pages.
@RicardoCenci
基本信息
Simple Model Context Protocol (MCP) server for Wiki.js
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"wikijs-mcp": {
"command": "npx",
"args": [
"wikijs-mcp"
],
"env": {
"WIKIJS_URL": "<YOUR WIKIJS URL>",
"WIKIJS_API_KEY": "<YOUR WIKIJS API TOKEN>"
}
}
}
}Search for pages in WikiJS by query string
Get a WikiJS page by its ID
Get a WikiJS page by its path and locale
Get all pages in WikiJS
A Model Context Protocol (MCP) server that integrates with WikiJS, allowing AI assistants to search and retrieve content from a WikiJS knowledge base.
Install via npm (npx wikijs-mcp) and configure with environment variables WIKIJS_URL and WIKIJS_API_KEY. For Cursor, add a JSON block in mcpServers. Obtain an API key from WikiJS Administration > API Access.
It is an MCP server that enables AI assistants to search and retrieve content from a WikiJS instance via four tools: search by query, get by ID, get by path/locale, and list all pages.
Log into your WikiJS instance as administrator, go to Administration > API Access, create a new API key with appropriate permissions, and copy the generated key to your `.env` file.
`WIKIJS_URL` (URL of your WikiJS instance) and `WIKIJS_API_KEY` (WikiJS API key) are both required.
Run `npx wikijs-mcp` from the command line. For Cursor, add the provided JSON configuration with your URL and API key.
The repository is at `https://github.com/RicardoCenci/wikijs-mcp.git` and is licensed under the MIT License.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

One permissioned folder your team and your AI agents both log into.
评论