calculator-mcp-server
Evaluate, simplify, and differentiate mathematical expressions via MCP. Provides a single tool for arithmetic, algebra, and symbolic differentiation with secure sandboxing.
README
<div align="center"> <h1>@cyanheads/calculator-mcp-server</h1> <p><b>Evaluate, simplify, and differentiate mathematical expressions via MCP. STDIO or Streamable HTTP.</b> <div>1 Tool • 1 Resource</div> </p> </div>
<div align="center">
</div>
<div align="center">
</div>
<div align="center">
Public Hosted Server: https://calculator.caseyjhand.com/mcp
</div>
Tools
One tool for all mathematical operations:
| Tool Name | Description |
|---|---|
calculate |
Evaluate math expressions, simplify algebraic expressions, or compute symbolic derivatives. |
calculate
A single tool covering 100% of the server's purpose. The operation parameter defaults to evaluate, so the common case is just { expression: "..." }.
- Evaluate — arithmetic, trigonometry, logarithms, statistics, matrices, complex numbers, unit conversion, combinatorics
- Simplify — reduce algebraic expressions symbolically (e.g.,
2x + 3x->5 * x). Supports algebraic and trigonometric identities - Derivative — compute symbolic derivatives (e.g.,
3x^2 + 2x + 1->6 * x + 2) - Variable scope via
scopeparameter:{ "x": 5, "y": 3 } - Configurable precision for numeric results
- Blank optional
variableandprecisionvalues from form-based MCP clients are treated as omitted
Resources
| URI Pattern | Description |
|---|---|
calculator://help |
Available functions, operators, constants, and syntax reference. |
Features
Built on @cyanheads/mcp-ts-core:
- Declarative tool definitions — single file per tool, framework handles registration and validation
- Unified error handling across all tools
- Structured logging with optional OpenTelemetry tracing
- Runs locally (stdio/HTTP) or in Docker
Calculator-specific:
- Hardened math.js v15 instance — dangerous functions disabled, evaluation sandboxed via
vm.runInNewContext()with timeout - No auth required — all operations are read-only and stateless
- Input validation: expression length limits, expression separator rejection (semicolons and newlines), variable name regex enforcement
- Result validation: blocked result types (functions, parsers, result sets), configurable max result size
- Scope sanitization: numeric-only values, prototype pollution prevention (blocked
__proto__,constructor, etc.)
Getting Started
Public Hosted Instance
A public instance is available at https://calculator.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:
{
"mcpServers": {
"calculator-mcp-server": {
"type": "streamable-http",
"url": "https://calculator.caseyjhand.com/mcp"
}
}
}
Self-Hosted / Local
Add to your MCP client config (e.g., claude_desktop_config.json):
{
"mcpServers": {
"calculator-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/calculator-mcp-server@latest"]
}
}
}
Prerequisites
- Bun v1.3.0 or higher
Installation
- Clone the repository:
git clone https://github.com/cyanheads/calculator-mcp-server.git
- Navigate into the directory:
cd calculator-mcp-server
- Install dependencies:
bun install
Configuration
| Variable | Description | Default |
|---|---|---|
CALC_MAX_EXPRESSION_LENGTH |
Maximum allowed expression string length (10–10,000). | 1000 |
CALC_EVALUATION_TIMEOUT_MS |
Maximum evaluation time in milliseconds (100–30,000). | 5000 |
CALC_MAX_RESULT_LENGTH |
Maximum result string length in characters (1,000–1,000,000). | 100000 |
MCP_TRANSPORT_TYPE |
Transport: stdio or http. |
stdio |
MCP_HTTP_PORT |
Port for HTTP server. | 3010 |
MCP_AUTH_MODE |
Auth mode: none, jwt, or oauth. |
none |
MCP_LOG_LEVEL |
Log level (RFC 5424). | info |
Running the Server
Local Development
-
Build and run the production version:
bun run build bun run start:http # or start:stdio -
Run checks and tests:
bun run devcheck # Lints, formats, type-checks bun run test # Runs test suite
Docker
docker build -t calculator-mcp-server .
docker run -p 3010:3010 calculator-mcp-server
Project Structure
| Directory | Purpose |
|---|---|
src/mcp-server/tools/ |
Tool definitions (*.tool.ts). |
src/mcp-server/resources/ |
Resource definitions (*.resource.ts). |
src/services/ |
Domain service integrations (MathService). |
src/config/ |
Environment variable parsing and validation with Zod. |
docs/ |
Generated directory tree. |
Development Guide
See AGENTS.md or CLAUDE.md for development guidelines and architectural rules. The short version:
- Handlers throw, framework catches — no
try/catchin tool logic - Use
ctx.logfor logging - Register new tools and resources in
src/index.ts
Contributing
Issues and pull requests are welcome. Run checks before submitting:
bun run devcheck
bun run test
License
Apache-2.0 — see LICENSE for details.
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。