@utilix-tech/mcp 0.32.0 → 0.34.0

package/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 Full release notes for all Utilix surfaces (browser tools, REST API, SDKs, MCP server) live at [utilix.tech/changelog](https://utilix.tech/changelog). This file tracks just this package.
 
+## 0.34.0
+- Add `lint_conventional_commit` tool: lint a git commit message against the Conventional Commits v1.0.0 spec, checking header format, blank-line separation, footer tokens, and BREAKING CHANGE casing.
+- Add `calculate_savings_goal` tool: solve for months to reach a savings goal at a fixed monthly contribution, or the monthly contribution required to hit a goal by a target month count.
+
+## 0.33.0
+- Add `analyze_sentence_lengths` tool: histogram of sentence lengths in words, plus mean, median, standard deviation, and a coefficient-of-variation consistency label, distinct from readability grade scores.
+- Add `format_few_shot_examples` tool: format input/output example pairs into a numbered, XML-tagged, or delimiter-separated few-shot prompt template.
+
 ## 0.32.0
 - Add `calculate_emi` tool: equated monthly installment, total interest, and a year-by-year principal/interest breakdown from principal, annual rate, and tenure in years or months.
 - Add `parse_markdown_front_matter` tool: split a Markdown document into its YAML front matter fields and body content, parsing scalars, inline arrays, and block lists.

package/README.md

@@ -1,6 +1,6 @@
 # @utilix-tech/mcp
 
-MCP server exposing 150 developer utility tools to Claude, Cursor, VS Code Copilot, and any [Model Context Protocol](https://modelcontextprotocol.io) compatible AI assistant.
+MCP server exposing 154 developer utility tools to Claude, Cursor, VS Code Copilot, and any [Model Context Protocol](https://modelcontextprotocol.io) compatible AI assistant.
 
 No API key required. All tools run locally. Requires Node.js 18 or later.
 
@@ -128,7 +128,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `generate_qr` | Generate a QR code as an SVG string |
 | `generate_random_data` | Generate random mock data: names, emails, UUIDs, IPs, etc. |
 
-### Text (13 tools)
+### Text (14 tools)
 | Tool | Description |
 |------|-------------|
 | `convert_case` | Convert text case: camelCase, snake_case, PascalCase, etc. |
@@ -144,6 +144,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `score_readability` | Score text with Flesch Reading Ease, Flesch-Kincaid Grade Level, and Gunning Fog Index |
 | `detect_filler_words` | Scan text for filler words, hedge phrases, and clichés with per-phrase counts and a density score |
 | `calculate_string_distance` | Compute the Levenshtein (or Damerau) edit distance and normalized similarity between two strings |
+| `analyze_sentence_lengths` | Split text into sentences and report a histogram of sentence lengths, plus mean, median, standard deviation, and a consistency label |
 
 ### Time (6 tools)
 | Tool | Description |
@@ -155,7 +156,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `convert_timezone` | Convert a date/time between timezones |
 | `convert_iso8601_duration` | Parse an ISO 8601 duration into components and total seconds, or format seconds into a duration string |
 
-### Units (21 tools)
+### Units (22 tools)
 | Tool | Description |
 |------|-------------|
 | `convert_bytes` | Convert between B, KB, MB, GB, TB, KiB, MiB, GiB, TiB |
@@ -179,6 +180,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `calculate_video_bitrate` | Calculate a video's file size from a bitrate and duration, or the bitrate needed to hit a target file size |
 | `calculate_rule_of_72` | Estimate years to double an investment from a rate, or the rate needed to double in a given number of years, via the Rule of 72 shortcut and the exact logarithmic result |
 | `calculate_emi` | Compute the Equated Monthly Installment for a loan from principal, annual rate, and tenure in years or months, with a year-by-year principal/interest breakdown |
+| `calculate_savings_goal` | Solve for months to reach a savings goal at a fixed monthly contribution, or the monthly contribution required to hit a goal by a target month count |
 
 ### API / Network (12 tools)
 | Tool | Description |
@@ -204,7 +206,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `color_palette` | Generate a color palette from a base color |
 | `color_shades` | Generate shades or tints from a base color |
 
-### Code (10 tools)
+### Code (11 tools)
 | Tool | Description |
 |------|-------------|
 | `format_sql` | Format a SQL query with proper indentation |
@@ -217,6 +219,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `lookup_mime` | Look up the MIME type for a file extension, or the extension(s) for a MIME type |
 | `parse_github_url` | Parse a github.com URL (repo, pull request, issue, commit, file, or release) into structured components |
 | `detect_redos` | Statically flag catastrophic-backtracking (ReDoS) risk in a regex: nested quantifiers, overlapping alternation, adjacent overlapping quantifiers |
+| `lint_conventional_commit` | Lint a commit message against the Conventional Commits v1.0.0 spec: header format, blank-line separation, footer tokens, and BREAKING CHANGE casing |
 
 ### Data (7 tools)
 | Tool | Description |
@@ -242,7 +245,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `unicode_inspect` | Inspect Unicode code points of a string |
 | `optimize_svg` | Optimize and minify an SVG string |
 
-### AI / Agent (26 tools)
+### AI / Agent (27 tools)
 | Tool | Description |
 |------|-------------|
 | `estimate_tokens` | Estimate token count and cost for an LLM prompt |
@@ -271,6 +274,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `compress_json` | Compress JSON for LLM context budgets |
 | `diff_json_detailed` | Diff two parsed JSON values, returning every path with its op and unchanged paths |
 | `vector_similarity` | Cosine similarity, dot product, and Euclidean / Manhattan distance between two numeric vectors |
+| `format_few_shot_examples` | Format input/output example pairs into a numbered, XML-tagged, or delimiter-separated few-shot prompt template |
 
 ### Image (3 tools)
 | Tool | Description |

package/dist/index.js

@@ -1092,6 +1092,30 @@ server.tool("chunk_text", "Split text into overlapping chunks for RAG.", { text:
 server.tool("extract_urls", "Extract all URLs from text or HTML.", { text: z.string() }, async ({ text: text2 }) => {
   return { content: [{ type: "text", text: JSON.stringify(extractUrls(text2), null, 2) }] };
 });
+function _formatFewShotExamples(examples, format, delimiter) {
+  const valid = (examples ?? []).filter((e) => e?.input?.trim() && e?.output?.trim());
+  if (valid.length === 0) return { formatted: "", exampleCount: 0, format };
+  let formatted;
+  if (format === "xml") {
+    formatted = valid.map((e) => `<example>
+  <input>${e.input.trim()}</input>
+  <output>${e.output.trim()}</output>
+</example>`).join("\n\n");
+  } else if (format === "delimiter") {
+    formatted = valid.map((e) => `Input: ${e.input.trim()}
+Output: ${e.output.trim()}`).join(`
+${delimiter}
+`);
+  } else {
+    formatted = valid.map((e, i) => `Example ${i + 1}:
+Input: ${e.input.trim()}
+Output: ${e.output.trim()}`).join("\n\n");
+  }
+  return { formatted, exampleCount: valid.length, format };
+}
+server.tool("format_few_shot_examples", "Format a list of input/output example pairs into a standard few-shot prompt template: numbered, XML-tagged, or delimiter-separated.", { examples: z.array(z.object({ input: z.string(), output: z.string() })), format: z.enum(["numbered", "xml", "delimiter"]).default("numbered"), delimiter: z.string().default("---") }, async ({ examples, format, delimiter }) => {
+  return { content: [{ type: "text", text: JSON.stringify(_formatFewShotExamples(examples, format, delimiter), null, 2) }] };
+});
 server.tool("sanitize_html", "Strip HTML tags, scripts, and event handlers for LLM ingestion.", { html: z.string(), keep_links: z.boolean().default(false) }, async ({ html, keep_links }) => {
   return { content: [{ type: "text", text: JSON.stringify(sanitizeHtml(html, keep_links), null, 2) }] };
 });
@@ -3138,6 +3162,74 @@ function _scoreReadability(input) {
 server.tool("score_readability", "Score text with Flesch Reading Ease, Flesch-Kincaid Grade Level, and Gunning Fog Index, using a heuristic syllable counter.", { text: z.string() }, async ({ text: input }) => {
   return { content: [{ type: "text", text: JSON.stringify(_scoreReadability(input), null, 2) }] };
 });
+function _splitIntoSentencesForLengthDist(text2) {
+  const matches = text2.match(/[^.!?]+[.!?]*/g);
+  if (!matches) return [];
+  return matches.map((s) => s.trim()).filter((s) => s.length > 0);
+}
+function _countWordsInSentenceForLengthDist(sentence) {
+  return (sentence.match(/[a-zA-Z']+/g) ?? []).length;
+}
+function _analyzeSentenceLengths(input) {
+  const sentences = _splitIntoSentencesForLengthDist(input);
+  const lengths = sentences.map(_countWordsInSentenceForLengthDist).filter((n) => n > 0);
+  if (lengths.length === 0) {
+    return {
+      sentenceCount: 0,
+      lengths: [],
+      minLength: 0,
+      maxLength: 0,
+      meanLength: 0,
+      medianLength: 0,
+      stdDev: 0,
+      coefficientOfVariation: 0,
+      consistency: "No sentences to analyze",
+      buckets: []
+    };
+  }
+  const sentenceCount = lengths.length;
+  const minLength = Math.min(...lengths);
+  const maxLength = Math.max(...lengths);
+  const meanLength = lengths.reduce((a, b) => a + b, 0) / sentenceCount;
+  const sorted = [...lengths].sort((a, b) => a - b);
+  const mid = Math.floor(sorted.length / 2);
+  const medianLength = sorted.length % 2 === 0 ? (sorted[mid - 1] + sorted[mid]) / 2 : sorted[mid];
+  const variance = lengths.reduce((sum, n) => sum + (n - meanLength) ** 2, 0) / sentenceCount;
+  const stdDev = Math.sqrt(variance);
+  const coefficientOfVariation = meanLength > 0 ? stdDev / meanLength : 0;
+  let consistency;
+  if (coefficientOfVariation < 0.3) consistency = "Consistent \u2014 sentence lengths vary little";
+  else if (coefficientOfVariation < 0.6) consistency = "Moderate variation in sentence length";
+  else consistency = "Highly variable sentence length";
+  const bucketWidth = 5;
+  const bucketCount = Math.max(1, Math.ceil(maxLength / bucketWidth));
+  const buckets = [];
+  for (let i = 0; i < bucketCount; i++) {
+    const min = i * bucketWidth + 1;
+    const max = (i + 1) * bucketWidth;
+    buckets.push({ label: `${min}-${max}`, min, max, count: 0 });
+  }
+  for (const len of lengths) {
+    const idx = Math.min(Math.floor((len - 1) / bucketWidth), bucketCount - 1);
+    buckets[idx].count++;
+  }
+  const round2 = (n) => Math.round(n * 100) / 100;
+  return {
+    sentenceCount,
+    lengths,
+    minLength,
+    maxLength,
+    meanLength: round2(meanLength),
+    medianLength: round2(medianLength),
+    stdDev: round2(stdDev),
+    coefficientOfVariation: round2(coefficientOfVariation),
+    consistency,
+    buckets
+  };
+}
+server.tool("analyze_sentence_lengths", "Split text into sentences and report a histogram of sentence lengths in words, plus mean, median, standard deviation, and a consistency label. Distinct from readability grade scores.", { text: z.string() }, async ({ text: input }) => {
+  return { content: [{ type: "text", text: JSON.stringify(_analyzeSentenceLengths(input), null, 2) }] };
+});
 var _ID3V1_GENRES = [
   "Blues",
   "Classic Rock",
@@ -5546,5 +5638,218 @@ server.tool(
     return text(JSON.stringify(result, null, 2));
   }
 );
+var _COMMIT_DEFAULT_TYPES_MCP = ["build", "chore", "ci", "docs", "feat", "fix", "perf", "refactor", "revert", "style", "test"];
+var _COMMIT_HEADER_RE_MCP = /^([A-Za-z][A-Za-z0-9-]*)(\(([^()]*)\))?(!)?: (.+)$/;
+var _COMMIT_FOOTER_LINE_RE_MCP = /^([A-Za-z][A-Za-z0-9-]*|BREAKING CHANGE)(: ?| #)(.*)$/;
+var _COMMIT_BREAKING_LOOKALIKE_RE_MCP = /^([A-Za-z][A-Za-z -]*?)(: | #)(.*)$/;
+var _COMMIT_BREAKING_TOKEN_RE_MCP = /^breaking[- ]change$/i;
+function _lintConventionalCommitMcp(message, types, maxHeaderLength) {
+  if (typeof message !== "string" || message.trim() === "") return { error: "message is required" };
+  if (message.length > 2e4) return { error: "message too long (max 20,000 chars)" };
+  const commitTypes = types && types.length > 0 ? types : _COMMIT_DEFAULT_TYPES_MCP;
+  const headerLimit = maxHeaderLength ?? 100;
+  const findings = [];
+  const lines = message.replace(/\r\n/g, "\n").split("\n");
+  const header = lines[0];
+  const match = header.match(_COMMIT_HEADER_RE_MCP);
+  const parsed = {
+    header,
+    type: null,
+    scope: null,
+    breaking: false,
+    description: null,
+    body: null,
+    footers: []
+  };
+  if (!match) {
+    findings.push({ rule: "header-format", severity: "error", message: "Header must match '<type>[(scope)][!]: <description>', e.g. 'feat(auth): add OAuth2 login'. A single space must follow the colon." });
+    return { message, valid: false, parsed, findings };
+  }
+  const [, type, scopeGroup, scope, bang, description] = match;
+  parsed.type = type;
+  if (scopeGroup !== void 0) {
+    const scopeContent = (scope ?? "").trim();
+    if (scopeContent === "") {
+      findings.push({ rule: "scope-empty", severity: "error", message: "Scope parentheses are present but empty; either remove the parentheses or put a scope inside them, e.g. fix(parser):." });
+    } else {
+      parsed.scope = scopeContent;
+    }
+  }
+  const trimmedDescription = description.trim();
+  if (trimmedDescription === "") {
+    findings.push({ rule: "subject-empty", severity: "error", message: "The description after the colon must not be empty." });
+  } else {
+    parsed.description = trimmedDescription;
+    if (trimmedDescription.endsWith(".")) {
+      findings.push({ rule: "subject-full-stop", severity: "warning", message: "The description should not end with a period." });
+    }
+  }
+  if (!commitTypes.includes(type.toLowerCase())) {
+    findings.push({ rule: "type-unknown", severity: "warning", message: `'${type}' is not one of the recognized types (${commitTypes.join(", ")}). This is only a convention, not a spec requirement, so a custom type is fine if your team has agreed on it.` });
+  }
+  if (type !== type.toLowerCase()) {
+    findings.push({ rule: "type-case", severity: "warning", message: "The type is conventionally lower-case. The spec itself is not case-sensitive about this, but nearly every tool and team defaults to lower-case." });
+  }
+  if (header.length > headerLimit) {
+    findings.push({ rule: "header-max-length", severity: "warning", message: `Header is ${header.length} characters, longer than the recommended maximum of ${headerLimit}.` });
+  }
+  let breaking = bang === "!";
+  if (lines.length > 1) {
+    if (lines[1].trim() !== "") {
+      findings.push({ rule: "missing-blank-line-before-body", severity: "error", message: "A blank line must separate the header from the body or footer." });
+    }
+    const rest = lines.slice(1).join("\n");
+    const paragraphs = rest.split(/\n{2,}/).map((p) => p.trim()).filter((p) => p !== "");
+    let footerParagraph = null;
+    if (paragraphs.length > 0) {
+      const last = paragraphs[paragraphs.length - 1];
+      const lastLines = last.split("\n");
+      if (lastLines.every((l) => _COMMIT_FOOTER_LINE_RE_MCP.test(l.trim()))) {
+        footerParagraph = last;
+        paragraphs.pop();
+      }
+    }
+    parsed.body = paragraphs.length > 0 ? paragraphs.join("\n\n") : null;
+    const footers2 = parsed.footers;
+    if (footerParagraph) {
+      for (const line of footerParagraph.split("\n")) {
+        const fm = line.trim().match(_COMMIT_FOOTER_LINE_RE_MCP);
+        if (!fm) continue;
+        const [, token, , value] = fm;
+        footers2.push({ token, value: value.trim() });
+      }
+    }
+    for (const f of footers2) {
+      if (_COMMIT_BREAKING_TOKEN_RE_MCP.test(f.token) && f.token !== "BREAKING CHANGE" && f.token !== "BREAKING-CHANGE") {
+        findings.push({ rule: "breaking-change-casing", severity: "error", message: `Found '${f.token}:' as a footer, but the spec requires the breaking-change token to be exactly 'BREAKING CHANGE' or 'BREAKING-CHANGE' (uppercase).` });
+      }
+    }
+    for (const p of paragraphs) {
+      for (const line of p.split("\n")) {
+        const bm = line.trim().match(_COMMIT_BREAKING_LOOKALIKE_RE_MCP);
+        if (bm && _COMMIT_BREAKING_TOKEN_RE_MCP.test(bm[1]) && bm[1] !== "BREAKING CHANGE") {
+          findings.push({ rule: "breaking-change-casing", severity: "error", message: `Found '${bm[1]}' near the end of the message, but it wasn't recognized as a breaking-change footer. The spec requires the exact uppercase token 'BREAKING CHANGE' (or 'BREAKING-CHANGE'), immediately followed by ': '.` });
+        }
+      }
+    }
+  }
+  const footers = parsed.footers;
+  const breakingFooter = footers.find((f) => f.token === "BREAKING CHANGE" || f.token === "BREAKING-CHANGE");
+  if (breakingFooter) {
+    breaking = true;
+    if (breakingFooter.value === "") {
+      findings.push({ rule: "breaking-change-empty", severity: "error", message: "A 'BREAKING CHANGE:' footer must be followed by a description of the breaking change." });
+    }
+  }
+  parsed.breaking = breaking;
+  const valid = !findings.some((f) => f.severity === "error");
+  return { message, valid, parsed, findings };
+}
+server.tool(
+  "lint_conventional_commit",
+  "Lint a commit message against the Conventional Commits v1.0.0 spec: header format (type(scope)!: description), blank-line separation before the body/footers, footer token format, and BREAKING CHANGE casing. Returns the parsed type/scope/description/body/footers plus a list of error and warning findings.",
+  {
+    message: z.string().describe("The full commit message: header, optional blank line, optional body, optional footers"),
+    types: z.array(z.string()).optional().describe("Override the recognized type list (default: build, chore, ci, docs, feat, fix, perf, refactor, revert, style, test). Unrecognized types are a warning, not an error."),
+    maxHeaderLength: z.number().optional().describe("Header length that triggers a warning (default 100)")
+  },
+  async ({ message, types, maxHeaderLength }) => {
+    const result = _lintConventionalCommitMcp(message, types, maxHeaderLength);
+    if ("error" in result) return errText(result);
+    return text(JSON.stringify(result, null, 2));
+  }
+);
+function _calculateSavingsGoalMcp(mode, goalAmount, currentSavings, annualInterestRatePercent, monthlyContribution, months) {
+  if (mode !== "time-to-goal" && mode !== "contribution-for-target") {
+    return { error: "mode must be 'time-to-goal' or 'contribution-for-target'" };
+  }
+  if (!Number.isFinite(goalAmount) || goalAmount <= 0) return { error: "goalAmount must be a finite number greater than zero" };
+  if (!Number.isFinite(currentSavings) || currentSavings < 0) return { error: "currentSavings must be a finite, non-negative number" };
+  if (!Number.isFinite(annualInterestRatePercent) || annualInterestRatePercent < 0) {
+    return { error: "annualInterestRatePercent must be a finite, non-negative number" };
+  }
+  const round4 = (n) => Math.round(n * 1e4) / 1e4;
+  const r = annualInterestRatePercent / 100 / 12;
+  if (mode === "time-to-goal") {
+    if (typeof monthlyContribution !== "number" || !Number.isFinite(monthlyContribution) || monthlyContribution < 0) {
+      return { error: "monthlyContribution must be a finite, non-negative number" };
+    }
+    let exactMonths;
+    if (currentSavings >= goalAmount) {
+      exactMonths = 0;
+    } else if (monthlyContribution === 0) {
+      if (r === 0) return { error: "monthlyContribution must be greater than zero when annualInterestRatePercent is zero, since savings would never grow toward the goal" };
+      if (currentSavings <= 0) return { error: "monthlyContribution must be greater than zero when currentSavings is zero, since there is nothing to compound" };
+      exactMonths = Math.log(goalAmount / currentSavings) / Math.log(1 + r);
+    } else if (r === 0) {
+      exactMonths = (goalAmount - currentSavings) / monthlyContribution;
+    } else {
+      const denom = currentSavings + monthlyContribution / r;
+      const x = (goalAmount + monthlyContribution / r) / denom;
+      exactMonths = Math.log(x) / Math.log(1 + r);
+    }
+    const monthsRounded = Math.max(0, Math.ceil(exactMonths));
+    const finalBalance = r === 0 ? currentSavings + monthlyContribution * monthsRounded : currentSavings * Math.pow(1 + r, monthsRounded) + monthlyContribution * ((Math.pow(1 + r, monthsRounded) - 1) / r);
+    const totalContributed2 = monthlyContribution * monthsRounded;
+    const totalInterestEarned2 = finalBalance - currentSavings - totalContributed2;
+    return {
+      mode,
+      goalAmount: round4(goalAmount),
+      currentSavings: round4(currentSavings),
+      annualInterestRatePercent: round4(annualInterestRatePercent),
+      monthlyContribution: round4(monthlyContribution),
+      months: round4(exactMonths),
+      monthsRounded,
+      years: round4(monthsRounded / 12),
+      totalContributed: round4(totalContributed2),
+      totalInterestEarned: round4(totalInterestEarned2),
+      finalBalance: round4(finalBalance)
+    };
+  }
+  if (typeof months !== "number" || !Number.isFinite(months) || !Number.isInteger(months) || months <= 0) {
+    return { error: "months must be a positive integer" };
+  }
+  const growthOfCurrentSavings = r === 0 ? currentSavings : currentSavings * Math.pow(1 + r, months);
+  let requiredMonthlyContribution;
+  if (growthOfCurrentSavings >= goalAmount) {
+    requiredMonthlyContribution = 0;
+  } else if (r === 0) {
+    requiredMonthlyContribution = (goalAmount - currentSavings) / months;
+  } else {
+    requiredMonthlyContribution = (goalAmount - growthOfCurrentSavings) * r / (Math.pow(1 + r, months) - 1);
+  }
+  const totalContributed = requiredMonthlyContribution * months;
+  const totalInterestEarned = goalAmount - currentSavings - totalContributed;
+  return {
+    mode,
+    goalAmount: round4(goalAmount),
+    currentSavings: round4(currentSavings),
+    annualInterestRatePercent: round4(annualInterestRatePercent),
+    monthlyContribution: round4(requiredMonthlyContribution),
+    months,
+    monthsRounded: months,
+    years: round4(months / 12),
+    totalContributed: round4(totalContributed),
+    totalInterestEarned: round4(totalInterestEarned),
+    finalBalance: round4(goalAmount)
+  };
+}
+server.tool(
+  "calculate_savings_goal",
+  'Standard time-value-of-money arithmetic for an ordinary annuity (contributions at the end of each month, compounded monthly). Mode "time-to-goal" solves for how many months it takes to reach a savings goal given a fixed monthly contribution; mode "contribution-for-target" solves for the monthly contribution required to reach the goal in a given number of months. Pure closed-form formulas, no live rate data.',
+  {
+    mode: z.enum(["time-to-goal", "contribution-for-target"]).describe("Which quantity to solve for"),
+    goalAmount: z.number().describe("The target savings amount (must be greater than zero)"),
+    currentSavings: z.number().describe("Current savings balance (cannot be negative)"),
+    annualInterestRatePercent: z.number().describe("Nominal annual interest rate as a percent, compounded monthly (cannot be negative)"),
+    monthlyContribution: z.number().optional().describe('Required for mode "time-to-goal": the fixed amount contributed each month'),
+    months: z.number().optional().describe('Required for mode "contribution-for-target": the target number of months (positive integer)')
+  },
+  async ({ mode, goalAmount, currentSavings, annualInterestRatePercent, monthlyContribution, months }) => {
+    const result = _calculateSavingsGoalMcp(mode, goalAmount, currentSavings, annualInterestRatePercent, monthlyContribution, months);
+    if ("error" in result) return errText(result);
+    return text(JSON.stringify(result, null, 2));
+  }
+);
 var transport = new StdioServerTransport();
 await server.connect(transport);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@utilix-tech/mcp",
-  "version": "0.32.0",
-  "description": "MCP server exposing 143 Utilix developer tools to Claude, Cursor, VS Code Copilot, and any MCP-compatible AI assistant.",
+  "version": "0.34.0",
+  "description": "MCP server exposing 152 Utilix developer tools to Claude, Cursor, VS Code Copilot, and any MCP-compatible AI assistant.",
   "author": "Utilix <hello@utilix.tech>",
   "license": "MIT",
   "homepage": "https://utilix.tech/mcp",