@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.
- package/LICENSE +22 -0
- package/README.md +368 -0
- package/build/__mocks__/embeddings.d.ts +17 -0
- package/build/__mocks__/embeddings.js +66 -0
- package/build/__mocks__/embeddings.js.map +1 -0
- package/build/config.d.ts +44 -0
- package/build/config.js +158 -0
- package/build/config.js.map +1 -0
- package/build/config.test.d.ts +1 -0
- package/build/config.test.js +165 -0
- package/build/config.test.js.map +1 -0
- package/build/crawler/auth.d.ts +128 -0
- package/build/crawler/auth.js +546 -0
- package/build/crawler/auth.js.map +1 -0
- package/build/crawler/auth.test.d.ts +1 -0
- package/build/crawler/auth.test.js +174 -0
- package/build/crawler/auth.test.js.map +1 -0
- package/build/crawler/base.d.ts +24 -0
- package/build/crawler/base.js +149 -0
- package/build/crawler/base.js.map +1 -0
- package/build/crawler/base.test.d.ts +1 -0
- package/build/crawler/base.test.js +234 -0
- package/build/crawler/base.test.js.map +1 -0
- package/build/crawler/browser-config.d.ts +2 -0
- package/build/crawler/browser-config.js +29 -0
- package/build/crawler/browser-config.js.map +1 -0
- package/build/crawler/browser-config.test.d.ts +1 -0
- package/build/crawler/browser-config.test.js +56 -0
- package/build/crawler/browser-config.test.js.map +1 -0
- package/build/crawler/cheerio.d.ts +11 -0
- package/build/crawler/cheerio.js +134 -0
- package/build/crawler/cheerio.js.map +1 -0
- package/build/crawler/chromium.d.ts +21 -0
- package/build/crawler/chromium.js +596 -0
- package/build/crawler/chromium.js.map +1 -0
- package/build/crawler/content-extractor-types.d.ts +25 -0
- package/build/crawler/content-extractor-types.js +2 -0
- package/build/crawler/content-extractor-types.js.map +1 -0
- package/build/crawler/content-extractors.d.ts +9 -0
- package/build/crawler/content-extractors.js +9 -0
- package/build/crawler/content-extractors.js.map +1 -0
- package/build/crawler/content-utils.d.ts +2 -0
- package/build/crawler/content-utils.js +22 -0
- package/build/crawler/content-utils.js.map +1 -0
- package/build/crawler/content-utils.test.d.ts +1 -0
- package/build/crawler/content-utils.test.js +99 -0
- package/build/crawler/content-utils.test.js.map +1 -0
- package/build/crawler/crawlee-crawler.d.ts +63 -0
- package/build/crawler/crawlee-crawler.js +342 -0
- package/build/crawler/crawlee-crawler.js.map +1 -0
- package/build/crawler/crawlee-crawler.test.d.ts +1 -0
- package/build/crawler/crawlee-crawler.test.js +280 -0
- package/build/crawler/crawlee-crawler.test.js.map +1 -0
- package/build/crawler/default-extractor.d.ts +4 -0
- package/build/crawler/default-extractor.js +26 -0
- package/build/crawler/default-extractor.js.map +1 -0
- package/build/crawler/default-extractor.test.d.ts +1 -0
- package/build/crawler/default-extractor.test.js +200 -0
- package/build/crawler/default-extractor.test.js.map +1 -0
- package/build/crawler/default.d.ts +11 -0
- package/build/crawler/default.js +138 -0
- package/build/crawler/default.js.map +1 -0
- package/build/crawler/docs-crawler.d.ts +26 -0
- package/build/crawler/docs-crawler.js +97 -0
- package/build/crawler/docs-crawler.js.map +1 -0
- package/build/crawler/docs-crawler.test.d.ts +1 -0
- package/build/crawler/docs-crawler.test.js +185 -0
- package/build/crawler/docs-crawler.test.js.map +1 -0
- package/build/crawler/factory.d.ts +6 -0
- package/build/crawler/factory.js +83 -0
- package/build/crawler/factory.js.map +1 -0
- package/build/crawler/github-pages-extractor.d.ts +4 -0
- package/build/crawler/github-pages-extractor.js +33 -0
- package/build/crawler/github-pages-extractor.js.map +1 -0
- package/build/crawler/github-pages-extractor.test.d.ts +1 -0
- package/build/crawler/github-pages-extractor.test.js +184 -0
- package/build/crawler/github-pages-extractor.test.js.map +1 -0
- package/build/crawler/github.d.ts +20 -0
- package/build/crawler/github.js +181 -0
- package/build/crawler/github.js.map +1 -0
- package/build/crawler/github.test.d.ts +1 -0
- package/build/crawler/github.test.js +326 -0
- package/build/crawler/github.test.js.map +1 -0
- package/build/crawler/puppeteer.d.ts +16 -0
- package/build/crawler/puppeteer.js +191 -0
- package/build/crawler/puppeteer.js.map +1 -0
- package/build/crawler/queue-manager.d.ts +43 -0
- package/build/crawler/queue-manager.js +169 -0
- package/build/crawler/queue-manager.js.map +1 -0
- package/build/crawler/queue-manager.test.d.ts +1 -0
- package/build/crawler/queue-manager.test.js +509 -0
- package/build/crawler/queue-manager.test.js.map +1 -0
- package/build/crawler/site-rules.d.ts +11 -0
- package/build/crawler/site-rules.js +104 -0
- package/build/crawler/site-rules.js.map +1 -0
- package/build/crawler/site-rules.test.d.ts +1 -0
- package/build/crawler/site-rules.test.js +139 -0
- package/build/crawler/site-rules.test.js.map +1 -0
- package/build/crawler/storybook-extractor.d.ts +34 -0
- package/build/crawler/storybook-extractor.js +767 -0
- package/build/crawler/storybook-extractor.js.map +1 -0
- package/build/crawler/storybook-extractor.test.d.ts +1 -0
- package/build/crawler/storybook-extractor.test.js +491 -0
- package/build/crawler/storybook-extractor.test.js.map +1 -0
- package/build/embeddings/fastembed.d.ts +25 -0
- package/build/embeddings/fastembed.js +188 -0
- package/build/embeddings/fastembed.js.map +1 -0
- package/build/embeddings/fastembed.test.d.ts +1 -0
- package/build/embeddings/fastembed.test.js +307 -0
- package/build/embeddings/fastembed.test.js.map +1 -0
- package/build/embeddings/openai.d.ts +8 -0
- package/build/embeddings/openai.js +56 -0
- package/build/embeddings/openai.js.map +1 -0
- package/build/embeddings/types.d.ts +4 -0
- package/build/embeddings/types.js +2 -0
- package/build/embeddings/types.js.map +1 -0
- package/build/index.d.ts +2 -0
- package/build/index.js +1007 -0
- package/build/index.js.map +1 -0
- package/build/index.test.d.ts +1 -0
- package/build/index.test.js +364 -0
- package/build/index.test.js.map +1 -0
- package/build/indexing/queue-manager.d.ts +36 -0
- package/build/indexing/queue-manager.js +86 -0
- package/build/indexing/queue-manager.js.map +1 -0
- package/build/indexing/queue-manager.test.d.ts +1 -0
- package/build/indexing/queue-manager.test.js +257 -0
- package/build/indexing/queue-manager.test.js.map +1 -0
- package/build/indexing/status.d.ts +39 -0
- package/build/indexing/status.js +207 -0
- package/build/indexing/status.js.map +1 -0
- package/build/indexing/status.test.d.ts +1 -0
- package/build/indexing/status.test.js +246 -0
- package/build/indexing/status.test.js.map +1 -0
- package/build/processor/content.d.ts +16 -0
- package/build/processor/content.js +286 -0
- package/build/processor/content.js.map +1 -0
- package/build/processor/content.test.d.ts +1 -0
- package/build/processor/content.test.js +369 -0
- package/build/processor/content.test.js.map +1 -0
- package/build/processor/markdown.d.ts +11 -0
- package/build/processor/markdown.js +256 -0
- package/build/processor/markdown.js.map +1 -0
- package/build/processor/markdown.test.d.ts +1 -0
- package/build/processor/markdown.test.js +312 -0
- package/build/processor/markdown.test.js.map +1 -0
- package/build/processor/metadata-parser.d.ts +37 -0
- package/build/processor/metadata-parser.js +245 -0
- package/build/processor/metadata-parser.js.map +1 -0
- package/build/processor/metadata-parser.test.d.ts +1 -0
- package/build/processor/metadata-parser.test.js +357 -0
- package/build/processor/metadata-parser.test.js.map +1 -0
- package/build/processor/processor.d.ts +8 -0
- package/build/processor/processor.js +190 -0
- package/build/processor/processor.js.map +1 -0
- package/build/processor/processor.test.d.ts +1 -0
- package/build/processor/processor.test.js +357 -0
- package/build/processor/processor.test.js.map +1 -0
- package/build/rag/cache.d.ts +10 -0
- package/build/rag/cache.js +10 -0
- package/build/rag/cache.js.map +1 -0
- package/build/rag/code-generator.d.ts +11 -0
- package/build/rag/code-generator.js +30 -0
- package/build/rag/code-generator.js.map +1 -0
- package/build/rag/context-assembler.d.ts +23 -0
- package/build/rag/context-assembler.js +113 -0
- package/build/rag/context-assembler.js.map +1 -0
- package/build/rag/docs-search.d.ts +55 -0
- package/build/rag/docs-search.js +380 -0
- package/build/rag/docs-search.js.map +1 -0
- package/build/rag/pipeline.d.ts +26 -0
- package/build/rag/pipeline.js +91 -0
- package/build/rag/pipeline.js.map +1 -0
- package/build/rag/query-processor.d.ts +14 -0
- package/build/rag/query-processor.js +57 -0
- package/build/rag/query-processor.js.map +1 -0
- package/build/rag/reranker.d.ts +55 -0
- package/build/rag/reranker.js +210 -0
- package/build/rag/reranker.js.map +1 -0
- package/build/rag/response-generator.d.ts +20 -0
- package/build/rag/response-generator.js +101 -0
- package/build/rag/response-generator.js.map +1 -0
- package/build/rag/retriever.d.ts +19 -0
- package/build/rag/retriever.js +111 -0
- package/build/rag/retriever.js.map +1 -0
- package/build/rag/validator.d.ts +22 -0
- package/build/rag/validator.js +128 -0
- package/build/rag/validator.js.map +1 -0
- package/build/rag/version-manager.d.ts +23 -0
- package/build/rag/version-manager.js +98 -0
- package/build/rag/version-manager.js.map +1 -0
- package/build/setupTests.d.ts +4 -0
- package/build/setupTests.js +50 -0
- package/build/setupTests.js.map +1 -0
- package/build/storage/storage.d.ts +38 -0
- package/build/storage/storage.js +700 -0
- package/build/storage/storage.js.map +1 -0
- package/build/storage/storage.test.d.ts +1 -0
- package/build/storage/storage.test.js +338 -0
- package/build/storage/storage.test.js.map +1 -0
- package/build/types/rag.d.ts +27 -0
- package/build/types/rag.js +2 -0
- package/build/types/rag.js.map +1 -0
- package/build/types.d.ts +120 -0
- package/build/types.js +2 -0
- package/build/types.js.map +1 -0
- package/build/util/content-utils.d.ts +31 -0
- package/build/util/content-utils.js +120 -0
- package/build/util/content-utils.js.map +1 -0
- package/build/util/content.d.ts +1 -0
- package/build/util/content.js +16 -0
- package/build/util/content.js.map +1 -0
- package/build/util/docs.d.ts +1 -0
- package/build/util/docs.js +26 -0
- package/build/util/docs.js.map +1 -0
- package/build/util/docs.test.d.ts +1 -0
- package/build/util/docs.test.js +49 -0
- package/build/util/docs.test.js.map +1 -0
- package/build/util/favicon.d.ts +6 -0
- package/build/util/favicon.js +88 -0
- package/build/util/favicon.js.map +1 -0
- package/build/util/favicon.test.d.ts +1 -0
- package/build/util/favicon.test.js +140 -0
- package/build/util/favicon.test.js.map +1 -0
- package/build/util/logger.d.ts +17 -0
- package/build/util/logger.js +72 -0
- package/build/util/logger.js.map +1 -0
- package/build/util/logger.test.d.ts +1 -0
- package/build/util/logger.test.js +46 -0
- package/build/util/logger.test.js.map +1 -0
- package/build/util/security.d.ts +312 -0
- package/build/util/security.js +719 -0
- package/build/util/security.js.map +1 -0
- package/build/util/security.test.d.ts +1 -0
- package/build/util/security.test.js +524 -0
- package/build/util/security.test.js.map +1 -0
- package/build/util/site-detector.d.ts +22 -0
- package/build/util/site-detector.js +42 -0
- package/build/util/site-detector.js.map +1 -0
- 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
|
+
}
|