Wikijs Mcp

Name: Wikijs Mcp
Author: RicardoCenci

Local

github.com/RicardoCenciMemory & Knowledge6Updated 61w ago

Repository

About Wikijs Mcp

Wikijs Mcp connects AI assistants to Wiki.js instances to search and retrieve wiki content. It can fetch pages by ID or path and locale, or list all pages, using stdio or streamable HTTP transport.

Key features

01Search pages by query
02Retrieve pages by ID
03Retrieve pages by path and locale
04List all wiki pages
05Use stdio or streamable HTTP

Use cases

01Find wiki pages on a topic
02Fetch a page by its ID
03Retrieve a localized page by path
04Connect over streamable HTTP

MCP support

The MCP server exposes Wiki.js search and page-retrieval tools to AI clients. It supports stdio and streamable HTTP transports.

#documentation #wikijs #mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "wikijs": {
      "command": "npx",
      "args": [
        "-y",
        "wikijs-mcp"
      ],
      "env": {
        "WIKIJS_URL": "<WIKIJS_URL>",
        "WIKIJS_API_KEY": "<WIKIJS_API_KEY>"
      }
    }
  }
}

Run commandnpx -y wikijs-mcp

Environment variables to set

WIKIJS_URL

WIKIJS_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npmwikijs-mcpstdio

Tools

Saved tool list · updated 2w ago

Parameter	Type	Required	Description
locale	string	No	Optional locale for the search (e.g., "en")
path	string	No	Optional path to limit search scope
query	string	Yes	Search query to find pages

Details

From the project README

WikiJS MCP Server

A Model Context Protocol (MCP) server that provides integration with WikiJS, allowing AI assistants to search and retrieve content from your WikiJS knowledge base.

Overview

This MCP server enables AI assistants to interact with WikiJS instances by providing tools to:

Search for pages by query string
Retrieve pages by ID
Retrieve pages by path and locale
Get all pages from the wiki

Configuration for Cursor

Stdio

{
  "mcpServers": {
    "wikijs-mcp": {
      "command": "npx",
        "args": [
            "wikijs-mcp"
        ],
        "env": {
            "WIKIJS_URL": <your wikijs url>,
            "WIKIJS_API_KEY": <your wikijs api key>
        }
    }
  }
}

Streamable Http

Host Machine

Start the server TRANSPORT_METHOD=streamable-http TRANSPORT_OPTIONS_PORT=8080 npx wikijs-mcp (See Environment Variables for all available variables)

IDE

{
  "mcpServers": {
    "wikijs-mcp": {
      "transport": "http-streamable",
      "name": "WikiJS MCP",
      "url": <your mcp host url with port>/mcp
    }
  }
}

Getting a WikiJS API Key

Log into your WikiJS instance as an administrator
Go to Administration > API Access
Create a new API key with appropriate permissions
Copy the generated key to your .env file

Development

Clone the repository:

git clone https://github.com/RicardoCenci/wikijs-mcp.git
cd wikijs-mcp

Install dependencies:

npm install

Copy the environment template and fill out its contents

cp env.example .env

Build the project If you have make installed:

make build

Deploy the WikiJS instance for testing

docker compose up -d

Usage

npx wikijs-mcp

Environment Variables

Variable	Description	Required	Allowed Values	Default
`WIKIJS_URL`	URL of your WikiJS instance	Yes	-	-
`WIKIJS_API_KEY`	WikiJS API key	Yes	-	-
`TRANSPORT_METHOD`	The transport method	No	stdio, streamable-http	stdio
`TRANSPORT_OPTIONS_CORS_ORIGIN`	Cors Origin (only on streamable-http)	No	-	*
`TRANSPORT_OPTIONS_CORS_HEADERS`	Cors Headers, comma separated (only on streamable-http)	No	-	Content-Type=mcp-session-id
`TRANSPORT_OPTIONS_CORS_METHODS`	Cors Methods, comma separated (only on streamable-http)	No	-	GET,POST,OPTIONS
`TRANSPORT_OPTIONS_SESSION_TIMEOUT_MS`	Session timeout (only on streamable-http)	No	-	60000

License

This project is licensed under the MIT License.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.