Skip to main content
Glama

calculator_tool

Perform mathematical calculations including basic expressions, statistics, geometry, finance, logic, number theory, combinatorics, probability, set theory, and complex numbers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
calculation_typeYesThe type of calculation to perform.
expressionNoThe mathematical expression to evaluate (for 'evaluate_expression').
statistics_operationNo
data_pointsNo
data_set_xNo
data_set_yNo
geometry_operationNo
radiusNo
lengthNo
widthNo
sideNo
financial_math_operationNo
principalNo
rateNoInterest rate as a percentage (e.g., 5 for 5%).
timeNoTime in years.
n_compounding_periodsNo
future_valueNo
logic_operationNo
operand_aNo
operand_bNo
number_theory_operationNo
number_aNo
number_bNo
number_theory_modulusNo
combinatorics_operationNo
n_valueNo
r_valueNo
probability_operationNo
probability_aNo
probability_bNo
probability_a_given_bNo
probability_b_given_aNo
set_theory_operationNo
set_aNo
set_bNo
complex_number_operationNo
complex_aNoFirst complex number (e.g., '3 + 4i').
complex_bNoSecond complex number (e.g., '1 - 2i').
precision_levelNo

Implementation Reference

  • The main handler function exported as default. It parses the request, sets precision, dispatches to specific helper functions based on calculation_type, and returns the result or error in MCP format.
    export default async function (request: any) {
        try {
            const { calculation_type, ...params } = request.params.arguments;
            const precisionLevel = params.precision_level || 64;
            Decimal.set({ precision: precisionLevel });
    
            let result;
    
            switch (calculation_type) {
                case "evaluate_expression":
                    if (!params.expression) throw new Error("An expression is required.");
                    result = evaluate(params.expression);
                    break;
                case "calculate_statistics":
                    result = handleStatistics(params);
                    break;
                case "perform_geometry":
                    result = handleGeometry(params);
                    break;
                case "perform_financial_math":
                    result = handleFinancialMath(params);
                    break;
                case "perform_logic_operations":
                    result = handleLogicOperations(params);
                    break;
                case "perform_number_theory":
                    result = handleNumberTheory(params);
                    break;
                case "perform_combinatorics":
                    result = handleCombinatorics(params);
                    break;
                case "calculate_probability":
                    result = handleProbability(params);
                    break;
                case "perform_set_theory":
                    result = handleSetTheory(params);
                    break;
                case "perform_complex_number":
                    result = handleComplexNumber(params);
                    break;
                default:
                    throw new Error(`Unsupported calculation type: ${calculation_type}`);
            }
    
            return {
                content: [{
                    type: "text",
                    text: JSON.stringify({ result }, null, 2),
                }],
            };
        } catch (error) {
            return {
                content: [{
                    type: "text",
                    text: JSON.stringify({ error: error instanceof Error ? error.message : String(error) }, null, 2),
                }],
                isError: true,
            };
        }
    }
  • The JSON schema defining the tool's input parameters, including calculation_type and specific params for each operation type.
    export const schema = {
        name: "calculator_tool",
        description: "A powerful universal calculator supporting basic expressions, statistics, geometry, finance, logic, number theory, combinatorics, probability, set theory, and complex numbers.",
        type: "object",
        properties: {
            calculation_type: {
                type: "string",
                enum: [
                    "evaluate_expression", "calculate_statistics", "perform_geometry",
                    "perform_financial_math", "perform_logic_operations", "perform_number_theory",
                    "perform_combinatorics", "calculate_probability", "perform_set_theory",
                    "perform_complex_number"
                ],
                description: "The type of calculation to perform.",
            },
            // Common params
            expression: { type: "string", description: "The mathematical expression to evaluate (for 'evaluate_expression')." },
            // Statistics params
            statistics_operation: { type: "string", enum: ["mean", "median", "mode", "standard_deviation", "variance", "correlation", "regression"] },
            data_points: { type: "array", items: { type: "number" } },
            data_set_x: { type: "array", items: { type: "number" } },
            data_set_y: { type: "array", items: { type: "number" } },
            // Geometry params
            geometry_operation: { type: "string", enum: ["area_circle", "area_rectangle", "volume_cube"] },
            radius: { type: "number" },
            length: { type: "number" },
            width: { type: "number" },
            side: { type: "number" },
            // Financial params
            financial_math_operation: { type: "string", enum: ["simple_interest", "compound_interest", "present_value", "future_value"] },
            principal: { type: "number" },
            rate: { type: "number", description: "Interest rate as a percentage (e.g., 5 for 5%)." },
            time: { type: "number", description: "Time in years." },
            n_compounding_periods: { type: "integer" },
            future_value: { type: "number" },
            // Logic params
            logic_operation: { type: "string", enum: ["AND", "OR", "NOT", "XOR"] },
            operand_a: { type: "boolean" },
            operand_b: { type: "boolean" },
            // Number Theory params
            number_theory_operation: { type: "string", enum: ["gcd", "lcm", "prime_factorization", "is_prime", "modular_exponentiation"] },
            number_a: { type: "integer" },
            number_b: { type: "integer" },
            number_theory_modulus: { type: "integer" },
            // Combinatorics params
            combinatorics_operation: { type: "string", enum: ["permutation", "combination", "factorial", "binomial_coefficient"] },
            n_value: { type: "integer" },
            r_value: { type: "integer" },
            // Probability params
            probability_operation: { type: "string", enum: ["probability_event", "conditional_probability", "bayes_theorem"] },
            probability_a: { type: "number" },
            probability_b: { type: "number" },
            probability_a_given_b: { type: "number" },
            probability_b_given_a: { type: "number" },
            // Set Theory params
            set_theory_operation: { type: "string", enum: ["union", "intersection", "difference", "symmetric_difference", "is_subset"] },
            set_a: { type: "array", items: { "anyOf": [{ "type": "number" }, { "type": "string" }] } },
            set_b: { type: "array", items: { "anyOf": [{ "type": "number" }, { "type": "string" }] } },
            // Complex Number params
            complex_number_operation: { type: "string", enum: ["add", "subtract", "multiply", "divide", "modulus", "argument", "conjugate"] },
            complex_a: { type: "string", description: "First complex number (e.g., '3 + 4i')." },
            complex_b: { type: "string", description: "Second complex number (e.g., '1 - 2i')." },
            // Global params
            precision_level: { type: "number", enum: [32, 64, 128], default: 64 },
        },
        required: ["calculation_type"]
    };
  • The loadTools function dynamically discovers and registers all tools from src/tools directory by filename (e.g., calculator_tool.ts -> calculator_tool), importing their default handler, schema, and destroy functions into global tools and handlers maps.
    export async function loadTools(reload: boolean = false): Promise<{ [key: string]: (request: ToolRequest) => Promise<ToolResponse> }> {
      // 如果是初始加载且已加载,则直接返回
      if (!reload && isLoaded) return;
    
      // 如果是重新加载,则重置状态
      if (reload) {
        for (const tool of tools) {
          await tool?.destroy?.();
          delete handlers[tool.name];
        }
        tools.length = 0;
        isLoaded = false;
      }
    
      // 获取所有工具文件
      const toolFiles = fs.readdirSync(toolsDir).filter(file => file.endsWith('.js') || file.endsWith('.ts'));
    
      // 加载每个工具
      for (const file of toolFiles) {
        const toolPath = path.join(toolsDir, file);
        try {
          // 如果是重新加载,清除模块缓存
          if (reload) clearModuleCache(toolPath);
    
          // 导入模块,重新加载时添加时间戳防止缓存
          const importPath = 'file://' + toolPath + (reload ? `?update=${Date.now()}` : '');
          const { default: tool, schema, destroy } = await import(importPath);
          const toolName = path.parse(toolPath).name;
    
          // 注册工具
          tools.push({
            name: toolName,
            description: tool.description,
            inputSchema: schema,
            destroy: destroy
          });
    
          // 注册处理函数
          handlers[toolName] = async (request: ToolRequest) => { return await tool(request); };
        } catch (error) {
          console.error(`Failed to ${reload ? 'reload' : 'load'} tool ${file}:`, error);
        }
      }
    
      isLoaded = true;
      if (reload) console.log(`Successfully reloaded ${tools.length} tools`);
    
      return handlers;
    }
  • Example helper function for statistics operations, one of many handle* functions that implement specific calculation categories called from the main handler.
    function handleStatistics(params: any) {
        const { statistics_operation, data_points, data_set_x, data_set_y } = params;
        if (!statistics_operation) throw new Error("A statistics operation is required.");
    
        const checkDataPoints = () => {
            if (!data_points || !Array.isArray(data_points) || data_points.length === 0) {
                throw new Error("A non-empty data_points array is required.");
            }
        };
        const checkDataSets = () => {
            if (!data_set_x || !data_set_y || data_set_x.length !== data_set_y.length || data_set_x.length === 0) {
                throw new Error("Two equal-length, non-empty datasets (data_set_x and data_set_y) are required.");
            }
        };
    
        switch (statistics_operation) {
            case "mean": checkDataPoints(); return mean(data_points);
            case "median": checkDataPoints(); return median(data_points);
            case "mode": checkDataPoints(); return mode(data_points);
            case "standard_deviation": checkDataPoints(); return std(data_points);
            case "variance": checkDataPoints(); return variance(data_points);
            case "correlation": checkDataSets(); return evaluate('corr(x, y)', { x: data_set_x, y: data_set_y });
            case "regression":
                checkDataSets();
                const n = data_set_x.length;
                const sumX = data_set_x.reduce((s, v) => s + v, 0);
                const sumY = data_set_y.reduce((s, v) => s + v, 0);
                const sumXY = data_set_x.reduce((s, v, i) => s + v * data_set_y[i], 0);
                const sumX2 = data_set_x.reduce((s, v) => s + v * v, 0);
                const slope = (n * sumXY - sumX * sumY) / (n * sumX2 - sumX * sumX);
                const intercept = (sumY - slope * sumX) / n;
                return { slope, intercept, equation: `y = ${round(slope, 4)}x + ${round(intercept, 4)}` };
            default: throw new Error(`Unsupported statistics operation: ${statistics_operation}`);
        }
    }
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/xiaoguomeiyitian/ToolBox'

If you have feedback or need assistance with the MCP directory API, please join our Discord server