@cosmocoder/mcp-web-docs 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (240) hide show
  1. package/LICENSE +22 -0
  2. package/README.md +368 -0
  3. package/build/__mocks__/embeddings.d.ts +17 -0
  4. package/build/__mocks__/embeddings.js +66 -0
  5. package/build/__mocks__/embeddings.js.map +1 -0
  6. package/build/config.d.ts +44 -0
  7. package/build/config.js +158 -0
  8. package/build/config.js.map +1 -0
  9. package/build/config.test.d.ts +1 -0
  10. package/build/config.test.js +165 -0
  11. package/build/config.test.js.map +1 -0
  12. package/build/crawler/auth.d.ts +128 -0
  13. package/build/crawler/auth.js +546 -0
  14. package/build/crawler/auth.js.map +1 -0
  15. package/build/crawler/auth.test.d.ts +1 -0
  16. package/build/crawler/auth.test.js +174 -0
  17. package/build/crawler/auth.test.js.map +1 -0
  18. package/build/crawler/base.d.ts +24 -0
  19. package/build/crawler/base.js +149 -0
  20. package/build/crawler/base.js.map +1 -0
  21. package/build/crawler/base.test.d.ts +1 -0
  22. package/build/crawler/base.test.js +234 -0
  23. package/build/crawler/base.test.js.map +1 -0
  24. package/build/crawler/browser-config.d.ts +2 -0
  25. package/build/crawler/browser-config.js +29 -0
  26. package/build/crawler/browser-config.js.map +1 -0
  27. package/build/crawler/browser-config.test.d.ts +1 -0
  28. package/build/crawler/browser-config.test.js +56 -0
  29. package/build/crawler/browser-config.test.js.map +1 -0
  30. package/build/crawler/cheerio.d.ts +11 -0
  31. package/build/crawler/cheerio.js +134 -0
  32. package/build/crawler/cheerio.js.map +1 -0
  33. package/build/crawler/chromium.d.ts +21 -0
  34. package/build/crawler/chromium.js +596 -0
  35. package/build/crawler/chromium.js.map +1 -0
  36. package/build/crawler/content-extractor-types.d.ts +25 -0
  37. package/build/crawler/content-extractor-types.js +2 -0
  38. package/build/crawler/content-extractor-types.js.map +1 -0
  39. package/build/crawler/content-extractors.d.ts +9 -0
  40. package/build/crawler/content-extractors.js +9 -0
  41. package/build/crawler/content-extractors.js.map +1 -0
  42. package/build/crawler/content-utils.d.ts +2 -0
  43. package/build/crawler/content-utils.js +22 -0
  44. package/build/crawler/content-utils.js.map +1 -0
  45. package/build/crawler/content-utils.test.d.ts +1 -0
  46. package/build/crawler/content-utils.test.js +99 -0
  47. package/build/crawler/content-utils.test.js.map +1 -0
  48. package/build/crawler/crawlee-crawler.d.ts +63 -0
  49. package/build/crawler/crawlee-crawler.js +342 -0
  50. package/build/crawler/crawlee-crawler.js.map +1 -0
  51. package/build/crawler/crawlee-crawler.test.d.ts +1 -0
  52. package/build/crawler/crawlee-crawler.test.js +280 -0
  53. package/build/crawler/crawlee-crawler.test.js.map +1 -0
  54. package/build/crawler/default-extractor.d.ts +4 -0
  55. package/build/crawler/default-extractor.js +26 -0
  56. package/build/crawler/default-extractor.js.map +1 -0
  57. package/build/crawler/default-extractor.test.d.ts +1 -0
  58. package/build/crawler/default-extractor.test.js +200 -0
  59. package/build/crawler/default-extractor.test.js.map +1 -0
  60. package/build/crawler/default.d.ts +11 -0
  61. package/build/crawler/default.js +138 -0
  62. package/build/crawler/default.js.map +1 -0
  63. package/build/crawler/docs-crawler.d.ts +26 -0
  64. package/build/crawler/docs-crawler.js +97 -0
  65. package/build/crawler/docs-crawler.js.map +1 -0
  66. package/build/crawler/docs-crawler.test.d.ts +1 -0
  67. package/build/crawler/docs-crawler.test.js +185 -0
  68. package/build/crawler/docs-crawler.test.js.map +1 -0
  69. package/build/crawler/factory.d.ts +6 -0
  70. package/build/crawler/factory.js +83 -0
  71. package/build/crawler/factory.js.map +1 -0
  72. package/build/crawler/github-pages-extractor.d.ts +4 -0
  73. package/build/crawler/github-pages-extractor.js +33 -0
  74. package/build/crawler/github-pages-extractor.js.map +1 -0
  75. package/build/crawler/github-pages-extractor.test.d.ts +1 -0
  76. package/build/crawler/github-pages-extractor.test.js +184 -0
  77. package/build/crawler/github-pages-extractor.test.js.map +1 -0
  78. package/build/crawler/github.d.ts +20 -0
  79. package/build/crawler/github.js +181 -0
  80. package/build/crawler/github.js.map +1 -0
  81. package/build/crawler/github.test.d.ts +1 -0
  82. package/build/crawler/github.test.js +326 -0
  83. package/build/crawler/github.test.js.map +1 -0
  84. package/build/crawler/puppeteer.d.ts +16 -0
  85. package/build/crawler/puppeteer.js +191 -0
  86. package/build/crawler/puppeteer.js.map +1 -0
  87. package/build/crawler/queue-manager.d.ts +43 -0
  88. package/build/crawler/queue-manager.js +169 -0
  89. package/build/crawler/queue-manager.js.map +1 -0
  90. package/build/crawler/queue-manager.test.d.ts +1 -0
  91. package/build/crawler/queue-manager.test.js +509 -0
  92. package/build/crawler/queue-manager.test.js.map +1 -0
  93. package/build/crawler/site-rules.d.ts +11 -0
  94. package/build/crawler/site-rules.js +104 -0
  95. package/build/crawler/site-rules.js.map +1 -0
  96. package/build/crawler/site-rules.test.d.ts +1 -0
  97. package/build/crawler/site-rules.test.js +139 -0
  98. package/build/crawler/site-rules.test.js.map +1 -0
  99. package/build/crawler/storybook-extractor.d.ts +34 -0
  100. package/build/crawler/storybook-extractor.js +767 -0
  101. package/build/crawler/storybook-extractor.js.map +1 -0
  102. package/build/crawler/storybook-extractor.test.d.ts +1 -0
  103. package/build/crawler/storybook-extractor.test.js +491 -0
  104. package/build/crawler/storybook-extractor.test.js.map +1 -0
  105. package/build/embeddings/fastembed.d.ts +25 -0
  106. package/build/embeddings/fastembed.js +188 -0
  107. package/build/embeddings/fastembed.js.map +1 -0
  108. package/build/embeddings/fastembed.test.d.ts +1 -0
  109. package/build/embeddings/fastembed.test.js +307 -0
  110. package/build/embeddings/fastembed.test.js.map +1 -0
  111. package/build/embeddings/openai.d.ts +8 -0
  112. package/build/embeddings/openai.js +56 -0
  113. package/build/embeddings/openai.js.map +1 -0
  114. package/build/embeddings/types.d.ts +4 -0
  115. package/build/embeddings/types.js +2 -0
  116. package/build/embeddings/types.js.map +1 -0
  117. package/build/index.d.ts +2 -0
  118. package/build/index.js +1007 -0
  119. package/build/index.js.map +1 -0
  120. package/build/index.test.d.ts +1 -0
  121. package/build/index.test.js +364 -0
  122. package/build/index.test.js.map +1 -0
  123. package/build/indexing/queue-manager.d.ts +36 -0
  124. package/build/indexing/queue-manager.js +86 -0
  125. package/build/indexing/queue-manager.js.map +1 -0
  126. package/build/indexing/queue-manager.test.d.ts +1 -0
  127. package/build/indexing/queue-manager.test.js +257 -0
  128. package/build/indexing/queue-manager.test.js.map +1 -0
  129. package/build/indexing/status.d.ts +39 -0
  130. package/build/indexing/status.js +207 -0
  131. package/build/indexing/status.js.map +1 -0
  132. package/build/indexing/status.test.d.ts +1 -0
  133. package/build/indexing/status.test.js +246 -0
  134. package/build/indexing/status.test.js.map +1 -0
  135. package/build/processor/content.d.ts +16 -0
  136. package/build/processor/content.js +286 -0
  137. package/build/processor/content.js.map +1 -0
  138. package/build/processor/content.test.d.ts +1 -0
  139. package/build/processor/content.test.js +369 -0
  140. package/build/processor/content.test.js.map +1 -0
  141. package/build/processor/markdown.d.ts +11 -0
  142. package/build/processor/markdown.js +256 -0
  143. package/build/processor/markdown.js.map +1 -0
  144. package/build/processor/markdown.test.d.ts +1 -0
  145. package/build/processor/markdown.test.js +312 -0
  146. package/build/processor/markdown.test.js.map +1 -0
  147. package/build/processor/metadata-parser.d.ts +37 -0
  148. package/build/processor/metadata-parser.js +245 -0
  149. package/build/processor/metadata-parser.js.map +1 -0
  150. package/build/processor/metadata-parser.test.d.ts +1 -0
  151. package/build/processor/metadata-parser.test.js +357 -0
  152. package/build/processor/metadata-parser.test.js.map +1 -0
  153. package/build/processor/processor.d.ts +8 -0
  154. package/build/processor/processor.js +190 -0
  155. package/build/processor/processor.js.map +1 -0
  156. package/build/processor/processor.test.d.ts +1 -0
  157. package/build/processor/processor.test.js +357 -0
  158. package/build/processor/processor.test.js.map +1 -0
  159. package/build/rag/cache.d.ts +10 -0
  160. package/build/rag/cache.js +10 -0
  161. package/build/rag/cache.js.map +1 -0
  162. package/build/rag/code-generator.d.ts +11 -0
  163. package/build/rag/code-generator.js +30 -0
  164. package/build/rag/code-generator.js.map +1 -0
  165. package/build/rag/context-assembler.d.ts +23 -0
  166. package/build/rag/context-assembler.js +113 -0
  167. package/build/rag/context-assembler.js.map +1 -0
  168. package/build/rag/docs-search.d.ts +55 -0
  169. package/build/rag/docs-search.js +380 -0
  170. package/build/rag/docs-search.js.map +1 -0
  171. package/build/rag/pipeline.d.ts +26 -0
  172. package/build/rag/pipeline.js +91 -0
  173. package/build/rag/pipeline.js.map +1 -0
  174. package/build/rag/query-processor.d.ts +14 -0
  175. package/build/rag/query-processor.js +57 -0
  176. package/build/rag/query-processor.js.map +1 -0
  177. package/build/rag/reranker.d.ts +55 -0
  178. package/build/rag/reranker.js +210 -0
  179. package/build/rag/reranker.js.map +1 -0
  180. package/build/rag/response-generator.d.ts +20 -0
  181. package/build/rag/response-generator.js +101 -0
  182. package/build/rag/response-generator.js.map +1 -0
  183. package/build/rag/retriever.d.ts +19 -0
  184. package/build/rag/retriever.js +111 -0
  185. package/build/rag/retriever.js.map +1 -0
  186. package/build/rag/validator.d.ts +22 -0
  187. package/build/rag/validator.js +128 -0
  188. package/build/rag/validator.js.map +1 -0
  189. package/build/rag/version-manager.d.ts +23 -0
  190. package/build/rag/version-manager.js +98 -0
  191. package/build/rag/version-manager.js.map +1 -0
  192. package/build/setupTests.d.ts +4 -0
  193. package/build/setupTests.js +50 -0
  194. package/build/setupTests.js.map +1 -0
  195. package/build/storage/storage.d.ts +38 -0
  196. package/build/storage/storage.js +700 -0
  197. package/build/storage/storage.js.map +1 -0
  198. package/build/storage/storage.test.d.ts +1 -0
  199. package/build/storage/storage.test.js +338 -0
  200. package/build/storage/storage.test.js.map +1 -0
  201. package/build/types/rag.d.ts +27 -0
  202. package/build/types/rag.js +2 -0
  203. package/build/types/rag.js.map +1 -0
  204. package/build/types.d.ts +120 -0
  205. package/build/types.js +2 -0
  206. package/build/types.js.map +1 -0
  207. package/build/util/content-utils.d.ts +31 -0
  208. package/build/util/content-utils.js +120 -0
  209. package/build/util/content-utils.js.map +1 -0
  210. package/build/util/content.d.ts +1 -0
  211. package/build/util/content.js +16 -0
  212. package/build/util/content.js.map +1 -0
  213. package/build/util/docs.d.ts +1 -0
  214. package/build/util/docs.js +26 -0
  215. package/build/util/docs.js.map +1 -0
  216. package/build/util/docs.test.d.ts +1 -0
  217. package/build/util/docs.test.js +49 -0
  218. package/build/util/docs.test.js.map +1 -0
  219. package/build/util/favicon.d.ts +6 -0
  220. package/build/util/favicon.js +88 -0
  221. package/build/util/favicon.js.map +1 -0
  222. package/build/util/favicon.test.d.ts +1 -0
  223. package/build/util/favicon.test.js +140 -0
  224. package/build/util/favicon.test.js.map +1 -0
  225. package/build/util/logger.d.ts +17 -0
  226. package/build/util/logger.js +72 -0
  227. package/build/util/logger.js.map +1 -0
  228. package/build/util/logger.test.d.ts +1 -0
  229. package/build/util/logger.test.js +46 -0
  230. package/build/util/logger.test.js.map +1 -0
  231. package/build/util/security.d.ts +312 -0
  232. package/build/util/security.js +719 -0
  233. package/build/util/security.js.map +1 -0
  234. package/build/util/security.test.d.ts +1 -0
  235. package/build/util/security.test.js +524 -0
  236. package/build/util/security.test.js.map +1 -0
  237. package/build/util/site-detector.d.ts +22 -0
  238. package/build/util/site-detector.js +42 -0
  239. package/build/util/site-detector.js.map +1 -0
  240. package/package.json +112 -0
@@ -0,0 +1,42 @@
1
+ export class StorybookDetector {
2
+ async canHandle(document) {
3
+ // Check for Storybook API
4
+ const hasStorybookAPI = typeof window.__STORYBOOK_CLIENT_API__ !== 'undefined';
5
+ // Check for Storybook-specific elements
6
+ const hasStorybookElements = document.querySelector('#storybook-root, .sbdocs, [data-nodetype="root"]') !== null ||
7
+ document.querySelector('meta[name="storybook-version"]') !== null ||
8
+ document.baseURI?.includes('path=/docs/') ||
9
+ document.baseURI?.includes('path=/story/');
10
+ return hasStorybookAPI || hasStorybookElements;
11
+ }
12
+ }
13
+ export class GitHubPagesDetector {
14
+ async canHandle(document) {
15
+ return window.location.hostname.includes('github.io') &&
16
+ document.querySelector('.markdown-body, .site-footer, .page-header') !== null;
17
+ }
18
+ }
19
+ export class DefaultDetector {
20
+ async canHandle(_document) {
21
+ return true; // Always matches as fallback
22
+ }
23
+ }
24
+ const detectors = [
25
+ { type: 'storybook', detector: new StorybookDetector() },
26
+ { type: 'github', detector: new GitHubPagesDetector() },
27
+ { type: 'default', detector: new DefaultDetector() }
28
+ ];
29
+ /**
30
+ * Detects the type of documentation site
31
+ * @param document The document to analyze
32
+ * @returns The detected site type
33
+ */
34
+ export async function detectSiteType(document) {
35
+ for (const { type, detector } of detectors) {
36
+ if (await detector.canHandle(document)) {
37
+ return type;
38
+ }
39
+ }
40
+ return 'default';
41
+ }
42
+ //# sourceMappingURL=site-detector.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"site-detector.js","sourceRoot":"","sources":["../../src/util/site-detector.ts"],"names":[],"mappings":"AASA,MAAM,OAAO,iBAAiB;IAC5B,KAAK,CAAC,SAAS,CAAC,QAAkB;QAChC,0BAA0B;QAC1B,MAAM,eAAe,GAAG,OAAQ,MAAc,CAAC,wBAAwB,KAAK,WAAW,CAAC;QAExF,wCAAwC;QACxC,MAAM,oBAAoB,GACxB,QAAQ,CAAC,aAAa,CAAC,kDAAkD,CAAC,KAAK,IAAI;YACnF,QAAQ,CAAC,aAAa,CAAC,gCAAgC,CAAC,KAAK,IAAI;YACjE,QAAQ,CAAC,OAAO,EAAE,QAAQ,CAAC,aAAa,CAAC;YACzC,QAAQ,CAAC,OAAO,EAAE,QAAQ,CAAC,cAAc,CAAC,CAAC;QAE7C,OAAO,eAAe,IAAI,oBAAoB,CAAC;IACjD,CAAC;CACF;AAED,MAAM,OAAO,mBAAmB;IAC9B,KAAK,CAAC,SAAS,CAAC,QAAkB;QAChC,OAAO,MAAM,CAAC,QAAQ,CAAC,QAAQ,CAAC,QAAQ,CAAC,WAAW,CAAC;YAC9C,QAAQ,CAAC,aAAa,CAAC,4CAA4C,CAAC,KAAK,IAAI,CAAC;IACvF,CAAC;CACF;AAED,MAAM,OAAO,eAAe;IAC1B,KAAK,CAAC,SAAS,CAAC,SAAmB;QACjC,OAAO,IAAI,CAAC,CAAC,6BAA6B;IAC5C,CAAC;CACF;AAED,MAAM,SAAS,GAAqD;IAClE,EAAE,IAAI,EAAE,WAAW,EAAE,QAAQ,EAAE,IAAI,iBAAiB,EAAE,EAAE;IACxD,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,IAAI,mBAAmB,EAAE,EAAE;IACvD,EAAE,IAAI,EAAE,SAAS,EAAE,QAAQ,EAAE,IAAI,eAAe,EAAE,EAAE;CACrD,CAAC;AAEF;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAAC,QAAkB;IACrD,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,SAAS,EAAE,CAAC;QAC3C,IAAI,MAAM,QAAQ,CAAC,SAAS,CAAC,QAAQ,CAAC,EAAE,CAAC;YACvC,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC"}
package/package.json ADDED
@@ -0,0 +1,112 @@
1
+ {
2
+ "name": "@cosmocoder/mcp-web-docs",
3
+ "version": "1.0.0",
4
+ "description": "MCP server for crawling and indexing web documentation - works with any website",
5
+ "keywords": [
6
+ "mcp",
7
+ "model-context-protocol",
8
+ "documentation",
9
+ "indexing",
10
+ "search",
11
+ "crawler",
12
+ "ai",
13
+ "llm",
14
+ "cursor",
15
+ "claude",
16
+ "semantic-search",
17
+ "vector-search"
18
+ ],
19
+ "homepage": "https://github.com/cosmocoder/mcp-web-docs#readme",
20
+ "bugs": {
21
+ "url": "https://github.com/cosmocoder/mcp-web-docs/issues"
22
+ },
23
+ "repository": {
24
+ "type": "git",
25
+ "url": "git+https://github.com/cosmocoder/mcp-web-docs.git"
26
+ },
27
+ "license": "MIT",
28
+ "author": "cosmocoder",
29
+ "type": "module",
30
+ "main": "build/index.js",
31
+ "types": "./build/index.d.ts",
32
+ "bin": {
33
+ "mcp-web-docs": "build/index.js"
34
+ },
35
+ "files": [
36
+ "build",
37
+ "README.md",
38
+ "LICENSE",
39
+ "CHANGELOG.md"
40
+ ],
41
+ "scripts": {
42
+ "build": "tsc && chmod +x build/index.js",
43
+ "start": "node build/index.js",
44
+ "dev": "tsc -w",
45
+ "lint": "eslint . --ext .js,.ts",
46
+ "lint:fix": "npm run lint -- --fix",
47
+ "test": "vitest run",
48
+ "test:watch": "vitest",
49
+ "test:ui": "vitest --ui",
50
+ "test:coverage": "vitest run --coverage",
51
+ "test:types": "tsc --noEmit",
52
+ "prettier": "prettier --write src/",
53
+ "prettier:ci": "prettier --check src/",
54
+ "clean": "rm -rf build",
55
+ "postinstall": "npx playwright install",
56
+ "prepare": "husky"
57
+ },
58
+ "dependencies": {
59
+ "@andersmyrmel/vard": "1.2.0",
60
+ "@lancedb/lancedb": "0.22.3",
61
+ "@modelcontextprotocol/sdk": "1.23.0",
62
+ "@mozilla/readability": "0.6.0",
63
+ "cheerio": "1.1.2",
64
+ "cli-progress": "3.12.0",
65
+ "crawlee": "3.15.3",
66
+ "default-browser": "5.4.0",
67
+ "fastembed": "2.0.0",
68
+ "jsdom": "27.2.0",
69
+ "node-html-markdown": "2.0.0",
70
+ "pdfjs-dist": "5.4.449",
71
+ "playwright": "1.57.0",
72
+ "quick-lru": "7.3.0",
73
+ "safe-regex2": "5.0.0",
74
+ "semver": "7.7.3",
75
+ "sqlite": "5.1.1",
76
+ "sqlite3": "5.1.7",
77
+ "typescript": "5.9.3",
78
+ "zod": "4.1.13"
79
+ },
80
+ "devDependencies": {
81
+ "@commitlint/cli": "20.2.0",
82
+ "@commitlint/config-conventional": "20.2.0",
83
+ "@eslint/js": "9.39.1",
84
+ "@types/cli-progress": "3.11.6",
85
+ "@types/jsdom": "27.0.0",
86
+ "@types/node": "22.15.29",
87
+ "@types/semver": "7.7.1",
88
+ "@vitest/coverage-v8": "4.0.15",
89
+ "eslint": "9.39.1",
90
+ "globals": "16.5.0",
91
+ "husky": "9.1.7",
92
+ "jiti": "2.6.1",
93
+ "lint-staged": "16.2.7",
94
+ "prettier": "3.7.4",
95
+ "typescript-eslint": "8.48.1",
96
+ "vitest": "4.0.15",
97
+ "vitest-fetch-mock": "0.4.5"
98
+ },
99
+ "engines": {
100
+ "node": ">=22.19.0"
101
+ },
102
+ "engine-strict": true,
103
+ "lint-staged": {
104
+ "src/**/*.md": [
105
+ "npm run prettier"
106
+ ],
107
+ "src/**/*.{js,ts}": [
108
+ "npm run lint:fix",
109
+ "npm run prettier"
110
+ ]
111
+ }
112
+ }