@utilix-tech/mcp 0.81.0 → 0.82.0

package/CHANGELOG.md

@@ -2,6 +2,9 @@
 
 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.
 
+## 0.82.0
+- Add `generate_robots_txt` tool: build a robots.txt file from User-agent groups with Allow/Disallow rules and an optional Crawl-delay, plus a list of Sitemap URLs. The generator-side sibling of `validate_robots_txt`.
+
 ## 0.81.0
 - Add `validate_fence_language_tags` tool: scan a Markdown document's fenced code blocks and flag a missing, unknown, or inconsistently-cased language tag against a curated list of common syntax-highlighter identifiers.
 - Add `count_sql_placeholders` tool: count positional (`?`, `$1`) and named (`:name`, `@name`) parameter placeholders in a SQL query, flagging mixed styles and numbered-sequence gaps or duplicates.

package/README.md

@@ -1,6 +1,6 @@
 # @utilix-tech/mcp
 
-MCP server exposing 257 developer utility tools to Claude, Cursor, VS Code Copilot, and any [Model Context Protocol](https://modelcontextprotocol.io) compatible AI assistant.
+MCP server exposing 258 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.
 
@@ -231,6 +231,7 @@ claude mcp add utilix -- npx -y @utilix-tech/mcp
 | `validate_sitemap` | Validate a sitemap.xml or sitemap index against the sitemaps.org protocol |
 | `split_sitemap` | Split a URL list exceeding the sitemaps.org 50,000-URL cap into multiple sitemap.xml files plus a sitemap index file |
 | `validate_robots_txt` | Validate a robots.txt file: User-agent groups, rules, and directive syntax |
+| `generate_robots_txt` | Generate a robots.txt file from User-agent groups with Allow/Disallow rules and an optional Crawl-delay, plus Sitemap URLs |
 | `parse_user_agent` | Parse a browser User-Agent string into browser, engine, OS, and device type |
 | `build_cache_control` | Build and explain an HTTP Cache-Control response header from directives (max-age, no-store, immutable, etc.) |
 | `build_referrer_policy` | Build and explain an HTTP Referrer-Policy header from one or more fallback-chain policy tokens |

package/dist/index.js

@@ -1895,6 +1895,58 @@ server.tool(
     return text(JSON.stringify(result, null, 2));
   }
 );
+function _generateRobotsTxt(groups, sitemaps) {
+  if (!Array.isArray(groups) || groups.length === 0) {
+    return { error: "At least one group with a user-agent is required" };
+  }
+  const lines = [];
+  for (const group of groups) {
+    const userAgents = (group.userAgents ?? []).map((a) => a.trim()).filter(Boolean);
+    if (userAgents.length === 0) return { error: "Each group needs at least one non-empty user-agent" };
+    for (const ua of userAgents) lines.push(`User-agent: ${ua}`);
+    const disallow = group.disallow ?? [];
+    const allow = group.allow ?? [];
+    if (disallow.length === 0 && allow.length === 0) {
+      lines.push("Disallow:");
+    } else {
+      for (const value of disallow) lines.push(`Disallow: ${value}`);
+      for (const value of allow) lines.push(`Allow: ${value}`);
+    }
+    if (group.crawlDelay !== void 0) {
+      if (!Number.isFinite(group.crawlDelay) || group.crawlDelay < 0) {
+        return { error: "crawlDelay must be a non-negative number" };
+      }
+      lines.push(`Crawl-delay: ${group.crawlDelay}`);
+    }
+    lines.push("");
+  }
+  for (const sitemap of sitemaps ?? []) {
+    if (!/^https?:\/\//i.test(sitemap)) {
+      return { error: `Sitemap URL "${sitemap}" must be absolute (start with http:// or https://)` };
+    }
+    lines.push(`Sitemap: ${sitemap}`);
+  }
+  while (lines.length > 0 && lines[lines.length - 1] === "") lines.pop();
+  return { text: lines.join("\n") + "\n" };
+}
+server.tool(
+  "generate_robots_txt",
+  "Generate a robots.txt file from one or more User-agent groups (each with Allow/Disallow rules and an optional Crawl-delay) plus a list of Sitemap URLs. The inverse of validate_robots_txt: a group with no Allow or Disallow rules gets an explicit empty Disallow line, the standard way to allow crawling everything.",
+  {
+    groups: z.array(z.object({
+      userAgents: z.array(z.string()).describe('User-agent tokens for this group, e.g. ["*"] or ["Googlebot"]'),
+      allow: z.array(z.string()).optional().describe('Allow rule paths, e.g. ["/admin/public"]'),
+      disallow: z.array(z.string()).optional().describe('Disallow rule paths, e.g. ["/admin"]'),
+      crawlDelay: z.number().optional().describe("Crawl-delay in seconds for this group")
+    })).describe("User-agent groups to emit, in order"),
+    sitemaps: z.array(z.string()).optional().describe("Absolute sitemap URLs to append as Sitemap directives")
+  },
+  async ({ groups, sitemaps }) => {
+    const result = _generateRobotsTxt(groups, sitemaps);
+    if ("error" in result) return errText(result);
+    return text(JSON.stringify(result, null, 2));
+  }
+);
 var _CARD_NETWORK_RULES = [
   { name: "American Express", lengths: [15], test: (d) => /^3[47]/.test(d) },
   { name: "Diners Club", lengths: [14], test: (d) => /^3(?:0[0-5]|[68])/.test(d) },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@utilix-tech/mcp",
-  "version": "0.81.0",
+  "version": "0.82.0",
   "description": "MCP server exposing 198 Utilix developer tools to Claude, Cursor, VS Code Copilot, and any MCP-compatible AI assistant.",
   "author": "Utilix <hello@utilix.tech>",
   "license": "MIT",