Symath-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Symath-MCPdifferentiate sin(x) * cos(x)"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Symath-MCP
English
Symath MCP Server — symbolic computation, calculus, linear algebra, number theory, statistics, and unit conversion via the Model Context Protocol.
Quick Start
stdio (Claude Desktop / Claude Code)
pip install symath-mcpAdd to your MCP client configuration:
{
"mcpServers": {
"math": {
"command": "symath-mcp"
}
}
}Streamable HTTP (server mode)
pip install symath-mcp
symath-mcp --transport streamable-httpOr with Docker:
docker compose up -dThe server listens on http://127.0.0.1:5109/mcp by default.
Tools
Tool | Description |
| Evaluate mathematical expressions with arbitrary precision |
| Solve equations and systems (algebraic, differential) |
| Integration, differentiation, limits, series |
| Eigenvalues, SVD, LU/QR decomposition, linear solve |
| Simplify, expand, factor, partial fractions |
| Prime factorization, GCD/LCM, Fibonacci, CRT |
| Descriptive stats, regression, probability distributions |
| Unit conversion and physical constants |
Environment Variables
Variable | Default | Description |
|
| Bind address (streamable-http mode) |
|
| Listen port (streamable-http mode) |
License
MIT
Related MCP server: Math MCP Server
中文
Symath MCP 服务器 — 通过 Model Context Protocol 提供符号计算、微积分、线性代数、数论、统计和单位换算。
快速开始
stdio 模式(Claude Desktop / Claude Code)
pip install symath-mcp在 MCP 客户端配置中添加:
{
"mcpServers": {
"math": {
"command": "symath-mcp"
}
}
}Streamable HTTP 模式(服务器)
pip install symath-mcp
symath-mcp --transport streamable-http或使用 Docker:
docker compose up -d默认监听 http://127.0.0.1:5109/mcp。
工具列表
工具 | 说明 |
| 计算数学表达式,支持任意精度 |
| 求解方程/方程组(代数、微分) |
| 积分、求导、极限、级数展开 |
| 特征值、SVD、LU/QR 分解、线性方程组 |
| 化简、展开、因式分解、部分分式 |
| 质因数分解、GCD/LCM、斐波那契、中国剩余定理 |
| 描述性统计、回归、概率分布 |
| 单位换算与物理常数查询 |
环境变量
变量 | 默认值 | 说明 |
|
| 绑定地址(streamable-http 模式) |
|
| 监听端口(streamable-http 模式) |
许可证
MIT
Available Tools
8 toolsmath_calculusA
微积分运算:积分、求导、极限、级数展开、求和、求积。
expression: 数学表达式,如 'x^2*sin(x)'、'sin(x)/x'、'1/n^2'。 variable: 变量名,默认 'x'。 operation: 'integrate'(积分)、'differentiate'(求导)、'limit'(极限)、 'series'(级数展开)、'sum'(求和)、'product'(求积)。 lower: 定积分下限 / 求和下限 / 级数点。 upper: 定积分上限 / 求和上限。 order: 求导阶数 / 级数展开阶数,默认 1。 point: 极限趋近点 / 级数展开中心点。
Inputs: expression (required), variable, operation, lower, +3 more. Returns: result
math_convertA
单位换算或物理常数查询。
value: 数值,如 '100'。 unit_from: 源单位,如 'miles'。 unit_to: 目标单位,如 'km'。 constant: 查询物理/数学常数名称。留空则列出所有可用常数。
示例: math_convert(value='100', unit_from='miles', unit_to='km') math_convert(value='32', unit_from='F', unit_to='C') math_convert(constant='speed_of_light') math_convert(constant='') ← 列出所有常数
支持的单位类别: 长度、质量、时间、温度、速度、力、能量、功率、压强、 面积、体积、角度、频率、数据量、浓度。
Inputs: value, unit_from, unit_to, constant. Returns: result
math_evalA
计算数学表达式。支持任意精度浮点、复数、符号运算。
expression: 数学表达式,支持算术、三角函数、对数、指数、特殊函数(gamma/erf/zeta)、 复数(I 为虚数单位)、无穷大(oo)、矩阵字面量等。 示例: 'sqrt(2)+sqrt(3)', 'sin(pi/6)+cos(pi/3)', 'gamma(0.5)', 'integrate(x^2*sin(x), (x,0,pi))', 'Matrix([[1,2],[3,4]]).det()' precision: 数值计算精度(小数位数),默认 50。 substitutions: 变量替换,格式 'x=5,y=10'。
Inputs: expression (required), precision, substitutions. Returns: result
math_manipulateA
表达式变换与化简。
expression: 数学表达式。 operation: simplify — 通用化简 expand — 展开 factor — 因式分解 cancel — 约分有理函数 apart — 部分分式分解 together — 通分 collect — 按变量合并同类项(会用 variable 参数或自动选主变量) trigsimp — 三角化简 radsimp — 根式化简 piecewise_fold — 分段函数折叠 domain — 求定义域 variable: 用于 collect 操作的变量名(可选,不填则自动选第一个自由变量)。
Inputs: expression (required), operation, variable. Returns: result
math_matrixA
矩阵与线性代数运算。
matrix: 矩阵,格式 '[[a,b],[c,d]]' 或 '[a,b;c,d]'。 operation: 支持的运算: eigenvalues — 特征值 eigenvectors — 特征向量 determinant — 行列式 inverse — 逆矩阵 rref — 简化行阶梯形 rank — 秩 nullspace — 零空间 charpoly — 特征多项式 transpose — 转置 solve_linear — 解线性方程组 Ax=b(需 vector 参数) svd — 奇异值分解 lu — LU 分解 qr — QR 分解 diagonalize — 对角化 jordan — Jordan 标准形 vector: 线性方程组右侧向量,格式 '[a,b,c]',仅 solve_linear 需要。
Inputs: matrix (required), operation, vector. Returns: result
math_number_theoryA
数论运算。
value: 整数值或参数,取决于 operation: 因式分解/factor:'1234567890' GCD/LCM:'1234,5678' 素数范围:'2,100' 离散对数:'base,value,modulus' 中国剩余定理:'r1,m1;r2,m2;...' operation: factor — 质因数分解 isprime — 素数判定 nextprime — 下一个素数 prevprime — 前一个素数 totient — 欧拉函数 φ(n) divisors — 所有因子 primitiveroot — 最小原根 gcd — 最大公约数 lcm — 最小公倍数 fibonacci — 第 n 个斐波那契数 bernoulli — 第 n 个伯努利数 npartitions — 整数分拆数 primorial — 素数阶乘(前 n 个素数之积) primepi — ≤ n 的素数个数 prime — 第 n 个素数 primerange — 范围内素数列表(格式 'a,b') crt — 中国剩余定理(格式 'r1,m1;r2,m2;...') legendre — Legendre 符号 (a|p),格式 'a,p' jacobi — Jacobi 符号 (a|n),格式 'a,n'
Inputs: value (required), operation. Returns: result
math_solveA
求解方程或方程组。
equation: 方程,支持三种写法: (1) 'x^2 - 4 = 0'(显式等式) (2) 'x^2 - 4'(隐式 = 0) (3) 方程组: 'x + y = 10, 2*x - y = 5' 配合 variables='x,y' (4) 微分方程: 'Derivative(f(x),x) + f(x)' 配合 function='f' variables: 待求解变量,默认 'x'。方程组用逗号分隔: 'x,y,z'。 equation_type: 'auto'(自动检测)、'algebraic'、'differential'、'system'。 function: 微分方程中的未知函数名,默认自动从表达式中提取(如 f(x) → f)。
Inputs: equation (required), variables, equation_type, function. Returns: result
math_statisticsA
统计与概率计算。
data: 数据集或分布描述。 数据集格式: '[1,2,3,4,5]' 或 '1,2,3,4,5'。 配对数据(回归/相关): '[[1,2],[3,4],[5,6]]' 或 '[1,2;3,4;5,6]'。 operation: describe — 描述性统计(均值、中位数、标准差、极值等) mean / median — 均值 / 中位数 std / variance — 标准差 / 方差 min / max / range — 最小值 / 最大值 / 极差 skewness / kurtosis — 偏度 / 峰度 quantile — 分位数(需 quantile 参数,如 0.25) correlation — Pearson 相关系数(需配对数据) linear_regression — 简单线性回归 y=ax+b(需配对数据) distribution: 概率分布查询,格式 '分布名,参数1=值,参数2=值,x=点'。 支持的分布: normal, exponential, binomial, poisson, uniform, gamma, beta, chi2, t, F。 示例: 'normal,mu=0,sigma=1,x=1.96' 操作: pdf, cdf, quantile, mean, variance, sample(需 n=数量)。
Inputs: data (required), operation. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
TDQS
Scored across 8 tools
Each tool addresses a distinct area of mathematics (calculus, conversion, evaluation, manipulation, matrices, number theory, solving, statistics). There is no overlap in functionality; descriptions clearly differentiate them.
All tool names follow the pattern 'math_<operation>' in snake_case, e.g., math_calculus, math_convert. This is consistent and predictable across all eight tools.
8 tools cover a broad range of mathematical operations without being excessive. Each tool has a clear purpose, and the count feels appropriate for a comprehensive math server.
The server covers calculus, algebra, linear algebra, number theory, statistics, unit conversion, expression manipulation, and equation solving. This is a very comprehensive set for a math server, with no obvious gaps.
Maintenance
Related MCP Connectors
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
Educational MCP server with 17 math/stats tools, visualizations, and persistent workspace
Math.js MCP — wraps the mathjs.org API (free, no auth)
Math MCP server for primality, factorization, Java templates, and integer multiplication.
Related MCP Servers
- AlicenseCqualityDmaintenanceAn MCP server that provides access to SymPy's symbolic mathematics library for advanced algebraic computations. It enables users to perform complex tasks such as symbolic simplification, calculus, equation solving, matrix operations, and number theory.10045 PyPIMIT
- AlicenseBqualityDmaintenanceA Python-based MCP server providing mathematical computation tools and plotting utilities for a wide range of math topics including calculus, matrix operations, statistics, and more.2213 PyPI5MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server that exposes 8 mathematical tools (arithmetic, algebra, calculus, matrix operations, statistics, probability, unit conversions) to any MCP-compatible AI agent, enabling mathematical computations without code.811 npm1MIT
- AlicenseBqualityDmaintenanceHigh-precision mathematics server for MCP clients, providing exact integer arithmetic, symbolic derivatives, and numerical calculus via LaTeX-style input.65 npm2MIT