Alloy MCP Server
Enables Claude to write, compile, and execute formal verification models in Alloy and read raw mathematical graph structures back into its context window.
README
Alloy MCP Server
A local Model Context Protocol (MCP) server that provides a headless bridge between Claude Desktop and the Alloy Analyzer (Kodkod SAT solver). This allows Claude to write, compile, and execute formal verification models and read the raw mathematical graph structures directly back into its context window.
Features
- Fast Syntax Checking: Validates Alloy grammar without booting the heavy SAT solver.
- Targeted Execution: Isolate and test specific
runorcheckcommands. - Raw Graph Extraction: Exposes the underlying atoms and relations (
ans.toString()) so the AI can reason about the counterexample structurally. - Black Box Logging: Automatically saves all system outputs and Java errors to a local text file for manual debugging.
Prerequisites
To run this server locally, you must have the following installed:
- Node.js (v18 or higher)
- Java Development Kit (JDK) (v11 or higher)
- Claude Desktop App
Installation & Setup
-
Clone the repository:
git clone (https://github.com/joel6603/alloy-mcp-server.git) cd alloy-mcp-server -
Install Node dependencies:
npm install -
Download the Alloy Engine: Download the official Alloy 6 .jar file from AlloyTools. Rename the file to org.alloytools.alloy.dist.jar. Place it directly in the root folder of this project.
-
Compile the Java Backend
On Windows:
javac -cp "org.alloytools.alloy.dist.jar;." RunAlloy.java
On Mac/Linux:
javac -cp "org.alloytools.alloy.dist.jar:." RunAlloy.java
-
Connecting to Claude Desktop: Windows: %APPDATA%\Claude\claude_desktop_config.json
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Add the server to your configuration, ensuring the absolute path points to where you cloned this repository:
JSON { "mcpServers": { "alloy": { "command": "node", "args": [ "D:/path/to/your/repo/alloy-mcp-server/index.js" ] } } }
Restart Claude Desktop completely.
Available MCP Tools:
check_alloy_syntax: Accepts raw .als code and instantly returns line/column syntax errors.
run_alloy_model: Accepts raw .als code and an optional command_name. Executes the SAT solver and returns the resulting instances or counterexamples as formatted text.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。