kirby
CLI-first MCP server for composer-based Kirby CMS projects — inspect blueprints/templates/plugins, interact with a real Kirby runtime, and use a bundled Kirby knowledge base.
How to use
The Kirby MCP server is a CLI-first solution tailored for Composer-based Kirby CMS projects. It allows you to inspect blueprints, templates, and plugins while interacting with a real Kirby runtime, making it an invaluable tool for developers looking to enhance their workflow in managing Kirby applications. Additionally, the server includes a bundled Kirby knowledge base to support your development efforts.
Once connected to the Kirby MCP server, you can leverage its capabilities to query and manipulate various aspects of your Kirby project. Use commands to inspect blueprints and templates, or explore installed plugins. The server is particularly effective for executing commands that require real-time interactions with your project’s runtime, allowing you to test modifications immediately and access documentation from the knowledge base.
How to install
Prerequisites
Before installing the Kirby MCP server, ensure you have Node.js installed on your machine. You can download it from nodejs.org.
Option A: Quick start with npx
To quickly start using the Kirby MCP server without global installation, use the following command:
npx -y bnomei/kirby-mcp
Option B: Global install alternative
If you prefer a global installation, you can clone the repository and run it from your local environment:
git clone https://github.com/bnomei/kirby-mcp.git
cd kirby-mcp
npm install
npm start
Additional notes
For optimal performance, ensure that your Kirby project is properly configured with Composer and that all dependencies are up to date. You might also want to set environment variables for local development to avoid permission issues. Common gotchas include ensuring that your project's directory structure adheres to Kirby's standards, as any deviations may lead to unexpected behavior.
Related MCP Servers
superset
IDE for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine
agent-deck
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
claude-scholar
Personal AI CLI configuration for academic research & software development. Supports Claude Code, OpenCode, and Codex CLI — covering the full research lifecycle from ideation to publication.
floop
Spreading activation memory for AI coding agents - corrections in, context-aware behaviors out.
devtap
Bridge build/dev process output to AI coding sessions via MCP — supports Claude Code, Codex, OpenCode, Gemini CLI, and aider
uxc
Universal API calling CLI for URL-first discovery and invocation across OpenAPI, gRPC, GraphQL, MCP, and JSON-RPC.