@utilix-tech/mcp 0.95.0 → 0.97.0

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.
 
+## 0.97.0
+- Add `calculate_position_size` tool: compute a trade's position size from account size, risk percent per trade, entry price, and stop-loss price, plus the risk/reward ratio against an optional target price.
+- Add `detect_weasel_words` tool: scan text for weasel words, vague hedging phrases that imply evidence or consensus without naming a checkable source, like "studies show" or "many experts believe".
+
+## 0.96.0
+- Add `validate_routing_number` tool: validate a 9-digit US bank routing number via its weighted mod-10 checksum, identifying the routing number's type and Federal Reserve district from its first two digits.
+- Add `audit_markdown_image_alt_text` tool: scan a Markdown document's inline images and flag alt text accessibility smells, missing/empty alt text, generic placeholder words, a redundant "image of" prefix, and alt text that's just the image's own filename.
+
 ## 0.95.0
 - Add `read_png_chunks` tool: walk a PNG's chunk stream directly from its bytes to report every chunk's type, offset, size, and CRC-32 validity, plus the decoded IHDR header and common ancillary chunks (tEXt, pHYs, gAMA, tIME, acTL).
 - Add `estimate_audio_file_size` tool: estimate an audio file's size before recording or exporting it, uncompressed PCM size from sample rate/bit depth/channels or compressed size from a target bitrate.

package/README.md

@@ -1,6 +1,6 @@
 # @utilix-tech/mcp
 
-MCP server exposing 283 developer utility tools to Claude, Cursor, VS Code Copilot, and any [Model Context Protocol](https://modelcontextprotocol.io) compatible AI assistant.
+MCP server exposing 287 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.
 
@@ -134,7 +134,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `generate_random_data` | Generate random mock data: names, emails, UUIDs, IPs, etc. |
 | `generate_csp_nonce` | Generate a cryptographically random CSP nonce with ready-to-paste header directive and script/style tag snippets |
 
-### Text (18 tools)
+### Text (19 tools)
 | Tool | Description |
 |------|-------------|
 | `convert_case` | Convert text case: camelCase, snake_case, PascalCase, etc. |
@@ -157,6 +157,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `analyze_keyword_density` | Count keyword/phrase frequency and density (occurrences per 100 words) across a block of text, with single-word or 2/3-word phrase modes |
 | `check_dash_usage` | Scan text for likely dash misuse: a hyphen surrounded by spaces, an unconverted double hyphen, and inconsistent spacing around em dashes across the same document |
 | `check_acronym_expansion` | Scan text for acronyms and flag any that are used before being expanded on first mention, or never expanded at all |
+| `detect_weasel_words` | Scan text for weasel words: vague hedging phrases that imply evidence or consensus without naming a checkable source, like "studies show" or "many experts believe" |
 
 ### Time (6 tools)
 | Tool | Description |
@@ -169,7 +170,7 @@ 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 (51 tools)
+### Units (53 tools)
 | Tool | Description |
 |------|-------------|
 | `convert_bytes` | Convert between B, KB, MB, GB, TB, KiB, MiB, GiB, TiB |
@@ -223,6 +224,8 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `detect_negative_amortization` | Given a loan's balance, annual rate, and a proposed monthly payment, check whether that payment covers the interest accruing each period; if not, report the shortfall and project how the balance grows instead of shrinking |
 | `calculate_sales_commission` | Compute a sales commission from either a flat percent rate applied to the whole sale amount, or a tiered (marginal) rate structure where each tier applies only to the slice of sales within it, plus an optional base salary added to the total payout |
 | `intersect_semver_ranges` | Determine whether two semver ranges overlap and, if so, the intersecting range, supporting the same caret/tilde/comparison-operator/exact-version syntax as the semver tool |
+| `validate_routing_number` | Validate a 9-digit US bank routing number (ABA/RTN) via its weighted mod-10 checksum, and identify its routing number type and Federal Reserve district |
+| `calculate_position_size` | Compute a trade's position size from account size, risk percent per trade, entry price, and stop-loss price, plus the risk/reward ratio against an optional target price |
 
 ### API / Network (55 tools)
 | Tool | Description |
@@ -328,7 +331,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `find_duplicate_lockfile_versions` | Parse an npm, yarn, or pnpm lockfile and report every package installed at more than one resolved version, with a count of install locations per version |
 | `summarize_git_diff_stat` | Parse `git diff --stat` / `git log --stat` output into structured per-file insertion/deletion counts plus overall totals |
 
-### Data (21 tools)
+### Data (22 tools)
 | Tool | Description |
 |------|-------------|
 | `validate_yaml` | Validate YAML syntax |
@@ -352,6 +355,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `validate_markdown_heading_hierarchy` | Scan a Markdown document's ATX headings and flag heading-structure issues: skipped levels, multiple H1s, empty headings, duplicate headings, and a document that doesn't start at H1 |
 | `check_markdown_internal_links` | Scan a Markdown document's ATX headings, compute the GitHub-style anchor slug for each, and check every [text](#slug) internal link against them, flagging links that point at a heading that doesn't exist |
 | `summarize_csv_column_stats` | Parse CSV/TSV data and compute per-column summary statistics: null/unique counts for every column, plus min/max/mean/median/standard deviation for numeric columns or the most common value for categorical ones |
+| `audit_markdown_image_alt_text` | Scan a Markdown document's inline images and flag alt text accessibility smells: missing/empty alt text, generic placeholder words, a redundant "image of"/"photo of" prefix, and alt text that's just the image's own filename |
 
 ### CSS (2 tools)
 | Tool | Description |

package/dist/index.js

@@ -15254,5 +15254,268 @@ server.tool(
     return text(JSON.stringify(result, null, 2));
   }
 );
+var _ABA_FEDERAL_RESERVE_BANKS_MCP = {
+  1: "Boston",
+  2: "New York",
+  3: "Philadelphia",
+  4: "Cleveland",
+  5: "Richmond",
+  6: "Atlanta",
+  7: "Chicago",
+  8: "St. Louis",
+  9: "Minneapolis",
+  10: "Kansas City",
+  11: "Dallas",
+  12: "San Francisco"
+};
+function _abaDistrictAndTypeMcp(prefix) {
+  if (prefix >= 1 && prefix <= 12) {
+    return { type: "primary", district: { code: prefix, bank: _ABA_FEDERAL_RESERVE_BANKS_MCP[prefix] } };
+  }
+  if (prefix >= 21 && prefix <= 32) {
+    const code = prefix - 20;
+    return { type: "thrift", district: { code, bank: _ABA_FEDERAL_RESERVE_BANKS_MCP[code] } };
+  }
+  if (prefix >= 61 && prefix <= 72) {
+    const code = prefix - 60;
+    return { type: "electronic", district: { code, bank: _ABA_FEDERAL_RESERVE_BANKS_MCP[code] } };
+  }
+  if (prefix === 80) return { type: "traveler-check", district: null };
+  return { type: "unknown", district: null };
+}
+function _formatRoutingNumberMcp(digits) {
+  return `${digits.slice(0, 4)} ${digits.slice(4, 8)} ${digits.slice(8)}`;
+}
+function _validateRoutingNumberMcp(input) {
+  if (!input || !input.trim()) return { error: "Input is empty" };
+  const digits = input.replace(/[\s-]/g, "");
+  if (!/^\d+$/.test(digits)) return { error: "Routing number must contain only digits, spaces, or hyphens" };
+  if (digits.length !== 9) return { error: `Routing number length (${digits.length}) must be exactly 9 digits` };
+  const d = digits.split("").map(Number);
+  const sum = 3 * (d[0] + d[3] + d[6]) + 7 * (d[1] + d[4] + d[7]) + 1 * (d[2] + d[5] + d[8]);
+  const checksumValid = sum % 10 === 0;
+  const prefix = Number(digits.slice(0, 2));
+  const { type, district } = _abaDistrictAndTypeMcp(prefix);
+  return {
+    valid: checksumValid,
+    checksumValid,
+    length: digits.length,
+    formatted: _formatRoutingNumberMcp(digits),
+    routingNumberType: type,
+    federalReserveDistrict: district
+  };
+}
+server.tool(
+  "validate_routing_number",
+  "Validate a 9-digit US bank routing number (ABA/RTN) via the weighted mod-10 checksum from the ABA's routing number specification. Also identifies the routing number's type and Federal Reserve district from its first two digits.",
+  { routingNumber: z.string().describe("The 9-digit routing number, with optional spaces or hyphens") },
+  async ({ routingNumber }) => {
+    const result = _validateRoutingNumberMcp(routingNumber);
+    if ("error" in result) return errText(result);
+    return text(JSON.stringify(result, null, 2));
+  }
+);
+var _MARKDOWN_IMAGE_RE_MCP = /!\[([^\]]*)\]\(([^)\s]+)(?:\s+"[^"]*")?\)/g;
+var _MARKDOWN_IMAGE_GENERIC_ALT_WORDS_MCP = /* @__PURE__ */ new Set([
+  "image",
+  "picture",
+  "photo",
+  "photograph",
+  "pic",
+  "img",
+  "graphic",
+  "screenshot",
+  "icon",
+  "logo"
+]);
+var _MARKDOWN_IMAGE_REDUNDANT_PREFIX_RE_MCP = /^(image|picture|photo|photograph)\s+of\s+/i;
+var _MARKDOWN_IMAGE_FILENAME_EXT_RE_MCP = /\.(png|jpe?g|gif|svg|webp|bmp|avif|tiff?)$/i;
+function _markdownImageBasenameWithoutExtMcp(src) {
+  const withoutQuery = src.split(/[?#]/)[0];
+  const file = withoutQuery.split("/").pop() ?? withoutQuery;
+  return file.replace(_MARKDOWN_IMAGE_FILENAME_EXT_RE_MCP, "");
+}
+function _auditMarkdownImageAltTextMcp(markdown) {
+  const lines = markdown.replace(/\r\n/g, "\n").split("\n");
+  const images = [];
+  const issues = [];
+  let inFence = false;
+  let fenceMarker = "";
+  lines.forEach((line, idx) => {
+    const fenceMatch = line.match(/^\s*(```+|~~~+)/);
+    if (fenceMatch) {
+      if (!inFence) {
+        inFence = true;
+        fenceMarker = fenceMatch[1][0];
+      } else if (fenceMatch[1][0] === fenceMarker) {
+        inFence = false;
+      }
+      return;
+    }
+    if (inFence) return;
+    const lineNo = idx + 1;
+    _MARKDOWN_IMAGE_RE_MCP.lastIndex = 0;
+    let match;
+    while ((match = _MARKDOWN_IMAGE_RE_MCP.exec(line)) !== null) {
+      const alt = match[1].trim();
+      const src = match[2];
+      images.push({ line: lineNo, alt, src });
+      if (alt === "") {
+        issues.push({
+          line: lineNo,
+          type: "empty-alt",
+          src,
+          message: `Image at line ${lineNo} has no alt text (src: ${src}). If this image is purely decorative, an intentionally empty alt is fine; otherwise it needs a description.`
+        });
+        continue;
+      }
+      if (_MARKDOWN_IMAGE_GENERIC_ALT_WORDS_MCP.has(alt.toLowerCase())) {
+        issues.push({
+          line: lineNo,
+          type: "generic-alt",
+          src,
+          message: `Alt text "${alt}" at line ${lineNo} is a generic placeholder and doesn't describe the image's content.`
+        });
+      }
+      if (_MARKDOWN_IMAGE_REDUNDANT_PREFIX_RE_MCP.test(alt)) {
+        issues.push({
+          line: lineNo,
+          type: "redundant-prefix",
+          src,
+          message: `Alt text "${alt}" at line ${lineNo} starts with a redundant prefix; screen readers already announce images, so "${alt.replace(_MARKDOWN_IMAGE_REDUNDANT_PREFIX_RE_MCP, "")}" reads better.`
+        });
+      }
+      const baseName = _markdownImageBasenameWithoutExtMcp(src);
+      if (_MARKDOWN_IMAGE_FILENAME_EXT_RE_MCP.test(alt) || baseName !== "" && alt.toLowerCase() === baseName.toLowerCase()) {
+        issues.push({
+          line: lineNo,
+          type: "filename-as-alt",
+          src,
+          message: `Alt text "${alt}" at line ${lineNo} looks like the image's own filename rather than a description.`
+        });
+      }
+    }
+  });
+  return { images, issues, imageCount: images.length };
+}
+server.tool(
+  "audit_markdown_image_alt_text",
+  'Scan a Markdown document\'s inline images (`![alt](src)`) and flag alt text accessibility smells: missing/empty alt text, a generic placeholder word used alone ("image", "photo"), alt text that\'s just the image\'s own filename, and a redundant "image of"/"photo of" prefix. Only inline image syntax is scanned; reference-style images and raw HTML `<img>` tags are not detected.',
+  { markdown: z.string().describe("The Markdown document to scan") },
+  async ({ markdown }) => {
+    const result = _auditMarkdownImageAltTextMcp(markdown);
+    return text(JSON.stringify(result, null, 2));
+  }
+);
+function _calculatePositionSizeMcp(input) {
+  const { accountSize, riskPercent, entryPrice, stopLossPrice, targetPrice } = input;
+  if (!(accountSize > 0)) return { error: "accountSize must be greater than 0" };
+  if (!(riskPercent > 0) || riskPercent > 100) return { error: "riskPercent must be greater than 0 and at most 100" };
+  if (!(entryPrice > 0)) return { error: "entryPrice must be greater than 0" };
+  if (!(stopLossPrice > 0)) return { error: "stopLossPrice must be greater than 0" };
+  if (entryPrice === stopLossPrice) return { error: "entryPrice and stopLossPrice must differ" };
+  if (targetPrice !== void 0 && !(targetPrice > 0)) return { error: "targetPrice must be greater than 0" };
+  const direction = stopLossPrice < entryPrice ? "long" : "short";
+  const riskAmount = accountSize * (riskPercent / 100);
+  const perUnitRisk = Math.abs(entryPrice - stopLossPrice);
+  const positionSizeUnits = Math.floor(riskAmount / perUnitRisk);
+  const positionValue = positionSizeUnits * entryPrice;
+  const dollarRisk = positionSizeUnits * perUnitRisk;
+  let riskRewardRatio = null;
+  let targetOnCorrectSide = null;
+  if (targetPrice !== void 0) {
+    const reward = Math.abs(targetPrice - entryPrice);
+    riskRewardRatio = Math.round(reward / perUnitRisk * 100) / 100;
+    targetOnCorrectSide = direction === "long" ? targetPrice > entryPrice : targetPrice < entryPrice;
+  }
+  return {
+    direction,
+    riskAmount: Math.round(riskAmount * 100) / 100,
+    perUnitRisk: Math.round(perUnitRisk * 1e4) / 1e4,
+    positionSizeUnits,
+    positionValue: Math.round(positionValue * 100) / 100,
+    dollarRisk: Math.round(dollarRisk * 100) / 100,
+    riskRewardRatio,
+    targetOnCorrectSide
+  };
+}
+server.tool(
+  "calculate_position_size",
+  "Compute a trade's position size from account size, risk percent per trade, entry price, and stop-loss price: the dollar risk divided by the per-unit stop distance, floored to a whole share/unit count. Also infers the trade direction (long/short) and, given an optional target price, the risk/reward ratio and whether the target sits on the correct side of entry.",
+  {
+    accountSize: z.number().describe("Total account size"),
+    riskPercent: z.number().describe("Percent of the account willing to risk on this trade (0-100)"),
+    entryPrice: z.number().describe("The planned entry price"),
+    stopLossPrice: z.number().describe("The stop-loss price; must differ from entryPrice"),
+    targetPrice: z.number().optional().describe("Optional take-profit price, used to compute the risk/reward ratio")
+  },
+  async ({ accountSize, riskPercent, entryPrice, stopLossPrice, targetPrice }) => {
+    const result = _calculatePositionSizeMcp({ accountSize, riskPercent, entryPrice, stopLossPrice, targetPrice });
+    if ("error" in result) return errText(result);
+    return text(JSON.stringify(result, null, 2));
+  }
+);
+var _WEASEL_PHRASES_MCP = [
+  "many experts believe",
+  "some experts say",
+  "experts agree",
+  "critics argue",
+  "studies show",
+  "studies have shown",
+  "research shows",
+  "research suggests",
+  "it is widely believed",
+  "it is widely known",
+  "it is widely regarded",
+  "it is generally accepted",
+  "it is often said",
+  "it has been suggested",
+  "it is said that",
+  "some say",
+  "some people believe",
+  "some people think",
+  "many believe",
+  "many people think",
+  "many claim",
+  "observers note",
+  "sources say",
+  "according to some",
+  "widely regarded as",
+  "many consider",
+  "some scientists believe",
+  "some argue",
+  "reportedly",
+  "allegedly"
+];
+function _weaselRegexMcp(phrase) {
+  const tokens = phrase.split(/\s+/).map((t) => t.replace(/[.*+?^${}()|[\]\\]/g, "\\$&"));
+  return new RegExp("\\b" + tokens.join("\\s+") + "\\b", "gi");
+}
+function _detectWeaselWordsMcp(input) {
+  const totalWords = (input.match(/[A-Za-z0-9']+/g) ?? []).length;
+  const matches = [];
+  for (const phrase of _WEASEL_PHRASES_MCP) {
+    const re = _weaselRegexMcp(phrase);
+    const indices = [];
+    let m;
+    while ((m = re.exec(input)) !== null) {
+      indices.push(m.index);
+      if (m.index === re.lastIndex) re.lastIndex++;
+    }
+    if (indices.length > 0) matches.push({ phrase, count: indices.length, indices });
+  }
+  matches.sort((a, b) => b.count - a.count || a.phrase.localeCompare(b.phrase));
+  const totalMatches = matches.reduce((s, x) => s + x.count, 0);
+  const density = totalWords > 0 ? Math.round(totalMatches / totalWords * 1e3) / 10 : 0;
+  return { totalWords, totalMatches, density, matches };
+}
+server.tool(
+  "detect_weasel_words",
+  `Scan text for weasel words: vague hedging phrases that imply evidence or consensus without naming a checkable source ("studies show", "many experts believe", "it is widely known"). Dictionary-based heuristic over a curated phrase list, distinct from detect_filler_words' "hedge" category, which covers personal uncertainty ("maybe", "I think") rather than unattributed third-party authority.`,
+  { text: z.string().describe("The text to scan for weasel words") },
+  async ({ text: input }) => {
+    return text(JSON.stringify(_detectWeaselWordsMcp(input), null, 2));
+  }
+);
 var transport = new StdioServerTransport();
 await server.connect(transport);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@utilix-tech/mcp",
-  "version": "0.95.0",
-  "description": "MCP server exposing 283 Utilix developer tools to Claude, Cursor, VS Code Copilot, and any MCP-compatible AI assistant.",
+  "version": "0.97.0",
+  "description": "MCP server exposing 287 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",