@v1nvn/readability-mcp 0.15.0 → 0.16.0

package/dist/index.js

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import { $ as outlineInputShape, A as extractListOutputShape, B as extractLinksInputShape, C as resolveLazyImages, D as chunkTextOutputShape, E as isElement, F as chunkTextInputSchema, G as extractSectionInputSchema, H as extractListInputShape, I as chunkTextInputShape, J as extractTablesInputShape, K as extractSectionInputShape, L as extractGridInputSchema, M as extractTablesOutputShape, N as outlineOutputShape, O as extractGridOutputShape, P as outputSchemaShape, Q as outlineInputSchema, R as extractGridInputShape, S as normalizeDocument, T as buildDocument, U as extractMetadataInputSchema, V as extractListInputSchema, W as extractMetadataInputShape, X as htmlToMarkdownInputShape, Y as htmlToMarkdownInputSchema, Z as localPathField, _ as detectGating, a as sanitizeHtml, at as registerResources, b as isReaderable, c as computeTextMetrics, d as renderTable, et as selectorsSchema, f as resolveHeaderKeys, g as absolutize, h as detectPagination, i as toMarkdown, it as toErrorResult, j as extractMetadataOutputShape, k as extractLinksOutputShape, l as nonEmpty, m as readHtmlFile, n as registerExtractTool, nt as logger, o as formatPayload, ot as loadConfig, p as resolveCellText, q as extractTablesInputSchema, r as truncateMarkdown, rt as ExtractionError, s as resolveMetadata, t as extractArticleFromHtml, tt as chunkMarkdown, u as parseTableMatrix, v as TraceCollector, w as resolveReadabilityOptions, x as applySelectors, y as assembleDiagnostics, z as extractLinksInputSchema } from "./assets/extract-CnKZr8QG.js";
+import { $ as outlineInputShape, A as extractListOutputShape, B as extractLinksInputShape, C as resolveLazyImages, D as chunkTextOutputShape, E as isElement, F as chunkTextInputSchema, G as extractSectionInputSchema, H as extractListInputShape, I as chunkTextInputShape, J as extractTablesInputShape, K as extractSectionInputShape, L as extractGridInputSchema, M as extractTablesOutputShape, N as outlineOutputShape, O as extractGridOutputShape, P as outputSchemaShape, Q as outlineInputSchema, R as extractGridInputShape, S as normalizeDocument, T as buildDocument, U as extractMetadataInputSchema, V as extractListInputSchema, W as extractMetadataInputShape, X as htmlToMarkdownInputShape, Y as htmlToMarkdownInputSchema, Z as localPathField, _ as detectGating, a as sanitizeHtml, at as registerResources, b as isReaderable, c as computeTextMetrics, d as renderTable, et as selectorsSchema, f as resolveHeaderKeys, g as absolutize, h as detectPagination, i as toMarkdown, it as toErrorResult, j as extractMetadataOutputShape, k as extractLinksOutputShape, l as nonEmpty, m as readHtmlFile, n as registerExtractTool, nt as logger, o as formatPayload, ot as loadConfig, p as resolveCellText, q as extractTablesInputSchema, r as truncateMarkdown, rt as ExtractionError, s as resolveMetadata, t as extractArticleFromHtml, tt as chunkMarkdown, u as parseTableMatrix, v as TraceCollector, w as resolveReadabilityOptions, x as applySelectors, y as assembleDiagnostics, z as extractLinksInputSchema } from "./assets/extract-C55iDWx1.js";
 import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
 import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
 import { z } from "zod";
@@ -1401,7 +1401,7 @@ function createServer() {
 }
 //#endregion
 //#region src/index.ts
-if (process.argv[2] === "extract") import("./assets/cli-B5p52u-S.js").then((m) => m.runCli(process.argv.slice(2))).then((code) => {
+if (process.argv[2] === "extract") import("./assets/cli-CCcnfTRC.js").then((m) => m.runCli(process.argv.slice(2))).then((code) => {
 	process.exit(code);
 }).catch((err) => {
 	process.stderr.write(`${err instanceof Error ? err.message : String(err)}\n`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@v1nvn/readability-mcp",
-  "version": "0.15.0",
+  "version": "0.16.0",
   "description": "MCP server that turns rendered (post-JS) HTML into clean Markdown + metadata via Readability, Turndown, and DOMPurify.",
   "type": "module",
   "main": "dist/index.js",
@@ -41,6 +41,8 @@
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.29.0",
     "@mozilla/readability": "^0.6.0",
+    "@v1nvn/agentic-core": "^0.16.0",
+    "commander": "^15.0.0",
     "dompurify": "^3.4.12",
     "jsdom": "^30.0.1",
     "remark-gfm": "^4.0.1",

package/dist/assets/cli-B5p52u-S.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"cli-B5p52u-S.js","names":[],"sources":["../../src/cli.ts"],"sourcesContent":["import { extractArticleFromHtml } from './tools/extract.js';\nimport { readHtmlFile } from './tools/html-source.js';\n\nimport type { CallToolResult } from '@modelcontextprotocol/sdk/types.js';\nimport type { Readable } from 'node:stream';\n\ntype CliFormat = 'html' | 'json' | 'md';\n\nexport interface ParsedArgs {\n  readonly file: string | undefined;\n  readonly format: CliFormat;\n  readonly maxChars: number | undefined;\n}\n\nconst USAGE =\n  'Usage: readability-mcp extract [file.html] [--format md|json|html] [--max-chars N]';\n\nconst FORMATS: readonly CliFormat[] = ['html', 'json', 'md'];\n\nfunction isCliFormat(value: string | undefined): value is CliFormat {\n  return value !== undefined && (FORMATS as readonly string[]).includes(value);\n}\n\n// `extract` is consumed by the caller; everything after it is parsed here.\n// Flag values are read with `.at()` (not `[]`) because the peek may advance\n// past the end for a trailing flag with no value; `.at()` surfaces that as\n// undefined where bracket indexing would not (noUncheckedIndexedAccess is off).\nexport function parseArgs(argv: readonly string[]): ParsedArgs | undefined {\n  let file: string | undefined;\n  let format: CliFormat = 'md';\n  let maxChars: number | undefined;\n\n  const rest = argv.slice(1);\n  for (let i = 0; i < rest.length; i++) {\n    const arg = rest[i];\n    if (arg === '--format') {\n      const value = rest.at(++i);\n      if (!isCliFormat(value)) {\n        return undefined;\n      }\n      format = value;\n    } else if (arg === '--max-chars') {\n      const value = rest.at(++i);\n      if (value === undefined) {\n        return undefined;\n      }\n      const n = Number(value);\n      if (!Number.isInteger(n)) {\n        return undefined;\n      }\n      maxChars = n;\n    } else if (arg.startsWith('--')) {\n      return undefined;\n    } else if (file === undefined) {\n      file = arg;\n    } else {\n      return undefined;\n    }\n  }\n\n  return { file, format, maxChars };\n}\n\n// The stream is injected rather than reading process.stdin directly so the\n// path is testable. Chunks may be Buffer (process.stdin) or string\n// (Readable.from), so both are handled.\nexport async function readHtml(\n  file: string | undefined,\n  stream: Readable,\n): Promise<string> {\n  if (file !== undefined) {\n    return readHtmlFile(file);\n  }\n  const chunks: string[] = [];\n  for await (const chunk of stream) {\n    if (typeof chunk === 'string') {\n      chunks.push(chunk);\n    } else {\n      chunks.push(Buffer.from(chunk as Uint8Array).toString('utf8'));\n    }\n  }\n  return chunks.join('');\n}\n\nfunction payloadText(result: CallToolResult): string {\n  const first = result.content.at(0);\n  return first !== undefined && 'text' in first ? first.text : '';\n}\n\nexport async function runCli(argv: readonly string[]): Promise<number> {\n  if (argv[0] !== 'extract') {\n    process.stderr.write(`${USAGE}\\n`);\n    return 2;\n  }\n\n  const parsed = parseArgs(argv);\n  if (parsed === undefined) {\n    process.stderr.write(`${USAGE}\\n`);\n    return 2;\n  }\n\n  try {\n    const html = await readHtml(parsed.file, process.stdin);\n    // json reuses the markdown pipeline; the structured object is serialized below.\n    const pipelineFormat = parsed.format === 'html' ? 'html' : 'markdown';\n    const result = extractArticleFromHtml({\n      html,\n      format: pipelineFormat,\n      ...(parsed.maxChars !== undefined ? { maxChars: parsed.maxChars } : {}),\n    });\n\n    if (result.isError) {\n      process.stderr.write(`${payloadText(result)}\\n`);\n      return 1;\n    }\n\n    if (parsed.format === 'json') {\n      process.stdout.write(\n        `${JSON.stringify(result.structuredContent, null, 2)}\\n`,\n      );\n    } else {\n      process.stdout.write(`${payloadText(result)}\\n`);\n    }\n    return 0;\n  } catch (err) {\n    process.stderr.write(\n      `${err instanceof Error ? err.message : String(err)}\\n`,\n    );\n    return 1;\n  }\n}\n"],"mappings":";;AAcA,IAAM,QACJ;AAEF,IAAM,UAAgC;CAAC;CAAQ;CAAQ;AAAI;AAE3D,SAAS,YAAY,OAA+C;CAClE,OAAO,UAAU,KAAA,KAAc,QAA8B,SAAS,KAAK;AAC7E;AAMA,SAAgB,UAAU,MAAiD;CACzE,IAAI;CACJ,IAAI,SAAoB;CACxB,IAAI;CAEJ,MAAM,OAAO,KAAK,MAAM,CAAC;CACzB,KAAK,IAAI,IAAI,GAAG,IAAI,KAAK,QAAQ,KAAK;EACpC,MAAM,MAAM,KAAK;EACjB,IAAI,QAAQ,YAAY;GACtB,MAAM,QAAQ,KAAK,GAAG,EAAE,CAAC;GACzB,IAAI,CAAC,YAAY,KAAK,GACpB;GAEF,SAAS;EACX,OAAO,IAAI,QAAQ,eAAe;GAChC,MAAM,QAAQ,KAAK,GAAG,EAAE,CAAC;GACzB,IAAI,UAAU,KAAA,GACZ;GAEF,MAAM,IAAI,OAAO,KAAK;GACtB,IAAI,CAAC,OAAO,UAAU,CAAC,GACrB;GAEF,WAAW;EACb,OAAO,IAAI,IAAI,WAAW,IAAI,GAC5B;OACK,IAAI,SAAS,KAAA,GAClB,OAAO;OAEP;CAEJ;CAEA,OAAO;EAAE;EAAM;EAAQ;CAAS;AAClC;AAKA,eAAsB,SACpB,MACA,QACiB;CACjB,IAAI,SAAS,KAAA,GACX,OAAO,aAAa,IAAI;CAE1B,MAAM,SAAmB,CAAC;CAC1B,WAAW,MAAM,SAAS,QACxB,IAAI,OAAO,UAAU,UACnB,OAAO,KAAK,KAAK;MAEjB,OAAO,KAAK,OAAO,KAAK,KAAmB,CAAC,CAAC,SAAS,MAAM,CAAC;CAGjE,OAAO,OAAO,KAAK,EAAE;AACvB;AAEA,SAAS,YAAY,QAAgC;CACnD,MAAM,QAAQ,OAAO,QAAQ,GAAG,CAAC;CACjC,OAAO,UAAU,KAAA,KAAa,UAAU,QAAQ,MAAM,OAAO;AAC/D;AAEA,eAAsB,OAAO,MAA0C;CACrE,IAAI,KAAK,OAAO,WAAW;EACzB,QAAQ,OAAO,MAAM,GAAG,MAAM,GAAG;EACjC,OAAO;CACT;CAEA,MAAM,SAAS,UAAU,IAAI;CAC7B,IAAI,WAAW,KAAA,GAAW;EACxB,QAAQ,OAAO,MAAM,GAAG,MAAM,GAAG;EACjC,OAAO;CACT;CAEA,IAAI;EACF,MAAM,OAAO,MAAM,SAAS,OAAO,MAAM,QAAQ,KAAK;EAEtD,MAAM,iBAAiB,OAAO,WAAW,SAAS,SAAS;EAC3D,MAAM,SAAS,uBAAuB;GACpC;GACA,QAAQ;GACR,GAAI,OAAO,aAAa,KAAA,IAAY,EAAE,UAAU,OAAO,SAAS,IAAI,CAAC;EACvE,CAAC;EAED,IAAI,OAAO,SAAS;GAClB,QAAQ,OAAO,MAAM,GAAG,YAAY,MAAM,EAAE,GAAG;GAC/C,OAAO;EACT;EAEA,IAAI,OAAO,WAAW,QACpB,QAAQ,OAAO,MACb,GAAG,KAAK,UAAU,OAAO,mBAAmB,MAAM,CAAC,EAAE,GACvD;OAEA,QAAQ,OAAO,MAAM,GAAG,YAAY,MAAM,EAAE,GAAG;EAEjD,OAAO;CACT,SAAS,KAAK;EACZ,QAAQ,OAAO,MACb,GAAG,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG,EAAE,GACtD;EACA,OAAO;CACT;AACF"}