Calculator Mcp Server

io.github.cyanheadsv0.5.0更新於 Oct 8, 2026

Evaluate, simplify, and differentiate mathematical expressions.

已驗證Streamable HTTP可網頁執行Developer Tools

概覽

AI 產生的概覽

讓助理對數學運算式求值、化簡與微分,支援矩陣、複數、單位和精確分數。

功能
只有一個 calculate 工具,提供三種操作:evaluate(預設)、simplify 和 derivative,微分需要指定變數名稱。它支援算術、三角函數、對數、統計、矩陣、複數、單位和組合數學,並可透過 scope 傳入數值變數,例如 x 等於 5。數值型別可選 number、BigNumber(64 位有效數字)或 Fraction(精確有理數),精度可設為 1 到 16 位有效數字。calculator://help 資源提供靜態語法參考。
適用情境
適合助理需要可靠數值或符號運算、而不是憑推測做算術的情境:核對計算結果、化簡代數式或求符號導數。公開託管端點無需安裝,也適合快速試用。
執行需求
可以使用公開託管的 Streamable HTTP 端點,也可以用 bunx、npx 或 Docker 在本機執行。README 將 Bun v1.4.0 或更高版本列為本機建置的前提。選用環境變數可調整限制與傳輸方式,包括 CALC_MAX_EXPRESSION_LENGTH、CALC_EVALUATION_TIMEOUT_MS、CALC_MAX_RESULT_LENGTH、MCP_TRANSPORT_TYPE、MCP_HTTP_HOST、MCP_HTTP_PORT、MCP_HTTP_ENDPOINT_PATH、MCP_AUTH_MODE 和 MCP_LOG_LEVEL。未宣告需要身分驗證。
安裝前請注意
相關操作被描述為唯讀且無狀態,也不要求任何憑證。自行以 HTTP 方式託管會暴露一個驗證模式預設為 none 的端點,若該端點可從 localhost 以外存取,應設定 MCP_AUTH_MODE。運算式和 scope 值會傳送到所設定的端點,包括公開託管端點。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Calculator Mcp Server,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "calculator-mcp-server": {
      "type": "http",
      "url": "https://calculator.caseyjhand.com/mcp"
    }
  }
}

README

@cyanheads/calculator-mcp-server

Evaluate, simplify, and differentiate mathematical expressions via MCP. STDIO or Streamable HTTP.

1 Tool • 1 Resource


Overview

Calculator powered by math.js. Verify numeric results, simplify algebraic expressions, and compute symbolic derivatives through one tool. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

ToolDescription
calculateEvaluate math expressions, simplify algebraic expressions, or compute symbolic derivatives.

Resources

ResourceDescription
calculator://helpAvailable functions, operators, constants, and syntax reference.

Capability reference

calculate tool

  • One expression per call. operation selects evaluate (default), simplify, or derivative; derivatives require variable (e.g. "x").
  • Evaluate arithmetic, trigonometry, logarithms, statistics, matrices, complex numbers, units, and combinatorics; assign numeric variables through scope, e.g. { "x": 5 }.
  • numericType selects number, BigNumber (64 significant digits, for values that overflow a 64-bit float), or Fraction (exact rationals). Fraction mode returns fraction_unsupported, with guidance to change numeric type, when a result has no exact rational value (sqrt(2)), the expression calls a function Fraction mode cannot compute (sqrt(4), 5!), or it uses a value Fraction mode holds only as a rounded float (pi, 2^(1/2)).
  • precision sets 1–16 significant digits for numeric results. Blank optional variable and precision values are treated as omitted; scope and precision do not affect symbolic operations.
  • Simplification includes algebraic and trigonometric identities (2x + 3x → 5 * x); unchanged: true identifies expressions the simplifier cannot reduce, including polynomial factoring and rational cancellation cases.
  • Returns the result string, result type, original expression, and operation. Validation failures include typed reasons and recovery hints.

calculator://help resource

  • Markdown reference for functions, operators, constants, units, and expression syntax; no parameters.
  • Examples cover scope, matrices, complex numbers, precision, and all three operations.
  • Cacheable for 24 hours with public scope (cacheHint) — static content that never changes at runtime.

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Calculator-specific:

  • Hardened math.js v15 instance — dangerous functions disabled, evaluation run under a vm timeout
  • No auth required — all operations are read-only and stateless
  • Input validation: expression length limits and rejection of multiple statements; matrix row separators and string contents remain valid
  • Result validation: blocked result types (functions, parsers, result sets), configurable max result size
  • Size limits: functions that build a matrix or string from a size, product, broadcast, index, or precision argument are capped per call, and each evaluation has a total element budget; oversized requests fail fast with result_too_large
  • Scope sanitization: numeric-only values, prototype pollution prevention (blocked __proto__, constructor, etc.)

Agent-friendly output:

  • Effective-call echo — every response echoes the expression and operation, plus which scope variables and what precision were applied, so agents can verify what was actually computed
  • Discriminated output contracts — unchanged: true on simplify flags a no-op result instead of silently returning the same expression
  • Typed error reasons — validation and evaluation failures carry a typed reason (e.g. fraction_unsupported, evaluation_timeout, disallowed_result_type) plus an actionable recovery hint, rather than a raw exception

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:

json
{  "mcpServers": {    "calculator-mcp-server": {      "type": "streamable-http",      "url": "https://calculator.caseyjhand.com/mcp"    }  }}

Self-Hosted / Local

Add one of the following to your MCP client configuration file:

json
{  "mcpServers": {    "calculator-mcp-server": {      "type": "stdio",      "command": "bunx",      "args": ["@cyanheads/calculator-mcp-server@latest"],      "env": {        "MCP_TRANSPORT_TYPE": "stdio",        "MCP_LOG_LEVEL": "info"      }    }  }}

Or with npx (no Bun required):

json
{  "mcpServers": {    "calculator-mcp-server": {      "type": "stdio",      "command": "npx",      "args": ["-y", "@cyanheads/calculator-mcp-server@latest"],      "env": {        "MCP_TRANSPORT_TYPE": "stdio",        "MCP_LOG_LEVEL": "info"      }    }  }}

Or with Docker:

json
{  "mcpServers": {    "calculator-mcp-server": {      "type": "stdio",      "command": "docker",      "args": [        "run", "-i", "--rm",        "-e", "MCP_TRANSPORT_TYPE=stdio",        "ghcr.io/cyanheads/calculator-mcp-server:latest"      ]    }  }}

For Streamable HTTP, set the transport and start the built server:

sh
MCP_HTTP_PORT=3010 bun run start:http# Server listens at http://localhost:3010/mcp

Prerequisites

Installation

  1. Clone the repository:
sh
git clone https://github.com/cyanheads/calculator-mcp-server.git
  1. Navigate into the directory:
sh
cd calculator-mcp-server
  1. Install dependencies:
sh
bun install

Configuration

VariableDescriptionDefault
CALC_MAX_EXPRESSION_LENGTHMaximum allowed expression string length (10–10,000).1000
CALC_EVALUATION_TIMEOUT_MSMaximum evaluation time in milliseconds (100–30,000).5000
CALC_MAX_RESULT_LENGTHMaximum result string length in characters (1,000–1,000,000).100000
MCP_TRANSPORT_TYPETransport: stdio or http.stdio
MCP_HTTP_HOSTHostname for the HTTP server.127.0.0.1
MCP_HTTP_PORTPort for HTTP server.3010
MCP_HTTP_ENDPOINT_PATHPath for the HTTP MCP endpoint./mcp
MCP_HTTP_MAX_BODY_BYTESMaximum inbound HTTP request size; 0 disables the limit.1048576
MCP_AUTH_MODEAuth mode: none, jwt, or oauth.none
MCP_SESSION_MODEauto, stateful, or stateless. The server declares stateless in code, so every launch path resolves the same way; setting this overrides that declaration.stateless
MCP_LOG_LEVELLog level (RFC 5424).info

See .env.example for optional session, resumability, logging, and telemetry settings.

Running the server

Local development

  • Build and run the production version:

    sh
    bun run buildbun run start:http   # or start:stdio
  • Run checks and tests:

    sh
    bun run devcheck     # Lints, formats, type-checksbun run test         # Runs test suite

Docker

sh
docker build -t calculator-mcp-server .docker run -p 3010:3010 calculator-mcp-server

The image defaults to Streamable HTTP on port 3010, stateless sessions, and logs at /var/log/calculator-mcp-server. OpenTelemetry dependencies are installed by default; build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

DirectoryPurpose
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.
tests/Calculation, configuration, and response-contract tests.

Development guide

See AGENTS.md or CLAUDE.md for development guidelines and architectural rules. The short version:

  • Handlers throw, framework catches — no try/catch in tool logic
  • Use ctx.log for logging
  • Register new tools and resources in src/index.ts

Contributing

Issues are welcome. Run checks before submitting:

sh
bun run devcheckbun run test

License

Apache-2.0 — see LICENSE for details.

來源:README.md,提交 752849e

工具

0
工具後設資料尚未被收錄。

版本歷史

3
  1. v0.5.0最新Sep 25, 2026
  2. v0.4.3Sep 19, 2026
  3. v0.4.2Sep 16, 2026