What is MCP?
MCP (Model Context Protocol) is an open protocol developed by Anthropic that allows AI models to safely interact with external services and tools.
@heAdz0r
基本情報
Model Context Protocol (MCP) server for Wiki.js integration via GraphQL API.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"wikijs": {
"command": "docker",
"transport": "http",
"url": "http://localhost:3200/mcp",
"events": "http://localhost:3200/mcp/events",
"cwd": "/path/to/your/wikijs-mcp-server",
"env": {
"WIKIJS_BASE_URL": "https://wiki.example.com",
"WIKIJS_TOKEN": "WikiJS-API-TOKEN"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
Wikijs Mcp Server is a Model Context Protocol (MCP) server that enables AI models and agents to interact with Wiki.js through its GraphQL API. It provides a unified interface for managing pages, users, and groups, and supports both STDIO and HTTP transports for integration with editors like Cursor and VS Code.
Clone the repository, run npm run setup to install dependencies and create the .env file, then edit .env with your Wiki.js base URL and API token. Start the HTTP server with npm start (or npm run server:stdio for STDIO mode). For Cursor IDE, ensure .cursor/mcp.json is configured with transport: "http", url, events, and your real API token.
MCP (Model Context Protocol) is an open protocol developed by Anthropic that allows AI models to safely interact with external services and tools.
Log into the Wiki.js admin panel, go to the "API" section, create a new API key with necessary permissions, and copy the token to both the `.env` file and `.cursor/mcp.json`.
Node.js version 18.0.0 or higher is required. The server runs on port 3200 by default for HTTP mode.
Run `npm test` for automated tests, or use `npm run client` or `npm run http-client` for manual testing. In HTTP mode, endpoints like `GET /tools` and `GET /health` are available.
STDIO for direct editor integration (VS Code) and HTTP for web integrations and Cursor IDE support.
Project context your AI can query through MCP — with source evidence.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

Model Context Protocol Servers
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
コメント