cal-mcp
用于计算数学表达式的MCP
Documentation
Cal Server
项目简介
`Cal Server` 是一个基于 `FastMCP` 框架构建的简单数学表达式计算服务,使用 Bun 运行时环境。它利用 `expr-eval` 库解析和计算用户输入的数学表达式,并通过标准输入输出(stdio)与外界交互。该项目旨在提供一个轻量、高效的计算工具,支持基本数学运算和内置常量。
功能
- 表达式计算:支持用户输入数学表达式并返回计算结果。
- 内置常量:
- 工具名称:`cal`。
- 参数:接受一个字符串类型的数学表达式(`exp`)。
依赖
- `fastmcp`:用于构建 MCP 服务。
- `expr-eval`:用于解析和计算数学表达式。
- `zod`:用于参数验证。
前置条件
- 确保已安装 Bun 运行时(推荐最新版本)。
安装
Installing via Smithery
To install cal-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @pwh-pwh/cal-mcp --client claudemcp客户端配置
"cal-mcp": {
"name": "计算",
"description": "",
"isActive": true,
"command": "bunx",
"args": [
"cal-mcp"
]
}Manual Installation
1. 克隆项目仓库:
git clone2. 进入项目目录并安装依赖:
bun install使用方法
1. 启动服务:
bun run index.ts服务将通过标准输入输出(stdio)运行。
2. 输入数学表达式:
3. 支持的表达式示例:
注意事项
- 输入的表达式必须是有效的数学表达式,否则可能抛出错误。
- 服务当前仅支持通过 `stdio` 交互。
- 项目使用 Bun 运行时,确保命令与 Bun 兼容。
Hosted deployment
A hosted deployment is available on Fronteir AI.
Frequently asked questions
What is cal-mcp?
cal-mcp is 用于计算数学表达式的MCP
How do I install cal-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is cal-mcp open source?
Yes — it is hosted on GitHub at https://github.com/pwh-pwh/cal-mcp and has 13 stars.
Related MCP tools
🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes.
MCP Aggregator, Orchestrator, Middleware, Gateway in one docker TypeScript-based implementation. Trusted by 1400+ developers.
Playwright MCP server TypeScript-based implementation. Trusted by 22000+ developers. Trusted by 22000+ developers. Trusted by 22000+ developers.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Ag...
Official Notion MCP Server TypeScript-based implementation. Trusted by 3400+ developers. Trusted by 3400+ developers. Trusted by 3400+ developers.
🤖 A visualization mcp contains 25+ visual charts using @antvis. Using for chart generation and data analysis. TypeScript-based implementation.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP