brave-real-browser-mcp-server 2.15.3 → 2.15.5

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/README.md CHANGED
@@ -4,15 +4,15 @@
4
4
 
5
5
  <div align="center">
6
6
 
7
- ![Version](https://img.shields.io/badge/version-2.14.0-blue.svg)
7
+ ![Version](https://img.shields.io/badge/version-2.15.4-blue.svg)
8
8
  ![Node](https://img.shields.io/badge/node-%3E%3D18.0.0-green.svg)
9
- ![Tools](https://img.shields.io/badge/tools-78-purple.svg)
9
+ ![Tools](https://img.shields.io/badge/tools-66-purple.svg)
10
10
  ![IDEs](https://img.shields.io/badge/AI_IDEs-15+-orange.svg)
11
11
  ![License](https://img.shields.io/badge/license-MIT-red.svg)
12
12
 
13
- **सभी AI IDEs के लिए Universal MCP Server | 78+ Tools | Browser Automation | Web Scraping | CAPTCHA Solving**
13
+ **सभी AI IDEs के लिए Universal MCP Server | 66+ Tools | Browser Automation | Web Scraping | CAPTCHA Solving**
14
14
 
15
- [Installation](#-installation) | [Quick Start](#-quick-start) | [Qoder AI Setup](#-qoder-ai---complete-integration-guide) | [Tools](#-available-tools-78) | [IDE Configurations](#-ide-configurations)
15
+ [Installation](#-installation) | [Quick Start](#-quick-start) | [Qoder AI Setup](#-qoder-ai---complete-integration-guide) | [Tools](#-available-tools-66) | [IDE Configurations](#-ide-configurations)
16
16
 
17
17
  </div>
18
18
 
@@ -23,7 +23,7 @@
23
23
  **Brave Real Browser MCP Server** एक powerful automation tool है जो:
24
24
 
25
25
  - ✅ **20+ AI IDEs में काम करता है** (Antigravity, Warp AI, Zed, Cursor, Claude, Windsurf, Cline, Qoder AI, etc.)
26
- - ✅ **78+ Automation Tools** - Browser control, scraping, CAPTCHA solving, video extraction
26
+ - ✅ **66+ Automation Tools** - Browser control, scraping, CAPTCHA solving, video extraction
27
27
  - ✅ **MCP Protocol (STDIO)** - Fast and secure local communication
28
28
  - ✅ **Auto-Detection** - Automatically detects your IDE
29
29
  - ✅ **Real Brave Browser** - Anti-detection features, bypass Cloudflare
@@ -146,10 +146,11 @@ npm install -g brave-real-browser-mcp-server@latest
146
146
 
147
147
  ```json
148
148
  {
149
- "mcp_servers": {
149
+ "context_servers": {
150
150
  "brave-real-browser": {
151
- "command": "npx",
152
- "args": ["-y", "brave-real-browser-mcp-server@latest"]
151
+ "command": "npx.cmd",
152
+ "args": ["-y", "brave-real-browser-mcp-server@latest"],
153
+ "env": {}
153
154
  }
154
155
  }
155
156
  }
@@ -189,7 +190,7 @@ npm install -g brave-real-browser-mcp-server@latest
189
190
 
190
191
  ---
191
192
 
192
- ## 🛠️ Available Tools (78)
193
+ ## 🛠️ Available Tools (66)
193
194
 
194
195
  ### 🌐 Browser Management (2 tools)
195
196
 
@@ -214,14 +215,13 @@ npm install -g brave-real-browser-mcp-server@latest
214
215
  | `random_scroll` | Human-like scrolling |
215
216
  | `solve_captcha` | Solve CAPTCHA (reCAPTCHA, hCaptcha, Turnstile, etc.) |
216
217
 
217
- ### 📄 Content Extraction (10 tools)
218
+ ### 📄 Content Extraction (9 tools)
218
219
 
219
220
  | Tool | Description |
220
221
  | -------------------------- | ----------------------------------------- |
221
222
  | `get_content` | Extract page content (HTML/Text/Markdown) |
222
223
  | `find_selector` | Find CSS selectors for elements |
223
224
  | `scrape_table` | Extract table data with headers |
224
- | `extract_list` | Extract list items |
225
225
  | `extract_json` | Extract JSON data from page |
226
226
  | `scrape_meta_tags` | Extract meta tags and SEO info |
227
227
  | `extract_schema` | Extract schema.org structured data |
@@ -284,7 +284,7 @@ npm install -g brave-real-browser-mcp-server@latest
284
284
  | `audio_captcha_solver` | Solve audio CAPTCHAs |
285
285
  | `puzzle_captcha_handler` | Handle puzzle CAPTCHAs |
286
286
 
287
- ### 🔧 Data Processing (9 tools)
287
+ ### 🔧 Data Processing (5 tools)
288
288
 
289
289
  | Tool | Description |
290
290
  | ------------------------- | ---------------------------------- |
@@ -293,28 +293,17 @@ npm install -g brave-real-browser-mcp-server@latest
293
293
  | `contact_extractor` | Extract contact information |
294
294
  | `schema_validator` | Validate data against schema |
295
295
  | `required_fields_checker` | Check for required fields |
296
- | `duplicate_remover` | Remove duplicate entries |
297
- | `data_deduplication` | Advanced deduplication |
298
- | `missing_data_handler` | Handle missing data |
299
- | `data_type_validator` | Validate data types |
300
296
 
301
- ### 📊 Data Quality (3 tools)
297
+ ### 📊 Data Quality (0 tools)
302
298
 
303
- | Tool | Description |
304
- | ---------------------- | ------------------------ |
305
- | `outlier_detection` | Detect data outliers |
306
- | `consistency_checker` | Check data consistency |
307
- | `data_quality_metrics` | Generate quality metrics |
299
+ *Advanced data quality tools removed for optimization.*
308
300
 
309
- ### 🤖 AI-Powered Tools (5 tools)
301
+ ### 🤖 AI-Powered Tools (2 tools)
310
302
 
311
303
  | Tool | Description |
312
304
  | -------------------------- | --------------------------- |
313
305
  | `smart_selector_generator` | Auto-generate CSS selectors |
314
306
  | `content_classification` | Classify content type |
315
- | `sentiment_analysis` | Analyze text sentiment |
316
- | `summary_generator` | Generate content summaries |
317
- | `translation_support` | Translate content |
318
307
 
319
308
  ### 🔎 Search & Filter (5 tools)
320
309
 
@@ -336,11 +325,10 @@ npm install -g brave-real-browser-mcp-server@latest
336
325
  | `sitemap_parser` | Parse and navigate sitemaps |
337
326
  | `breadcrumb_navigator` | Navigate using breadcrumbs |
338
327
 
339
- ### 🔒 Session Management (7 tools)
328
+ ### 🔒 Session Management (6 tools)
340
329
 
341
330
  | Tool | Description |
342
331
  | ----------------------- | -------------------------- |
343
- | `cookie_manager` | Manage cookies |
344
332
  | `session_persistence` | Persist sessions |
345
333
  | `form_auto_fill` | Auto-fill forms |
346
334
  | `ajax_content_waiter` | Wait for AJAX content |
@@ -348,25 +336,21 @@ npm install -g brave-real-browser-mcp-server@latest
348
336
  | `login_session_manager` | Manage login sessions |
349
337
  | `shadow_dom_extractor` | Extract Shadow DOM content |
350
338
 
351
- ### 📸 Visual Tools (5 tools)
339
+ ### 📸 Visual Tools (4 tools)
352
340
 
353
341
  | Tool | Description |
354
342
  | ---------------------- | --------------------------- |
355
- | `full_page_screenshot` | Full page screenshot |
356
343
  | `element_screenshot` | Screenshot specific element |
357
344
  | `pdf_generation` | Generate PDF from page |
358
345
  | `video_recording` | Record page as video |
359
- | `visual_comparison` | Compare screenshots |
360
346
 
361
- ### 📈 Monitoring & Reporting (6 tools)
347
+ ### 📈 Monitoring & Reporting (3 tools)
362
348
 
363
349
  | Tool | Description |
364
350
  | ----------------------- | ------------------------- |
365
351
  | `progress_tracker` | Track automation progress |
366
352
  | `success_rate_reporter` | Report success rates |
367
- | `data_quality_metrics` | Data quality metrics |
368
353
  | `performance_monitor` | Monitor performance |
369
- | `monitoring_summary` | Get monitoring summary |
370
354
 
371
355
  ### 🛡️ Advanced Extraction & Obfuscation (4 tools)
372
356
 
@@ -376,11 +360,8 @@ npm install -g brave-real-browser-mcp-server@latest
376
360
  | `multi_layer_redirect_trace` | Trace multi-layer redirects |
377
361
  | `ad_protection_detector` | Detect ad protection |
378
362
 
379
-
380
363
  ## 🔧 Environment Variables
381
364
 
382
-
383
-
384
365
  You can configure the server using the local `.env` file directly.
385
366
 
386
367
  Edit `.env` to set your preferences:
@@ -401,9 +382,9 @@ PROXY_URL=http://localhost:8080
401
382
 
402
383
  ## 📊 Supported Protocols
403
384
 
404
- || Protocol | Used By | Auto-Config | Status |
405
- || --------------- | --------------------------------------------- | ----------- | ---------- |
406
- || **MCP (STDIO)** | Claude Desktop, Cursor, Windsurf, Cline, Warp | ✅ | 🟢 Working |
385
+ | Protocol | Used By | Auto-Config | Status |
386
+ | --------------- | --------------------------------------------- | ----------- | ---------- |
387
+ | **MCP (STDIO)** | Claude Desktop, Cursor, Windsurf, Cline, Warp | ✅ | 🟢 Working |
407
388
 
408
389
  ## 📄 License
409
390
 
@@ -126,110 +126,3 @@ export async function handleContentClassification(args) {
126
126
  return { content: [{ type: 'text', text: `❌ Error: ${error.message}` }], isError: true };
127
127
  }
128
128
  }
129
- /**
130
- * Sentiment Analysis - Analyze sentiment of page content (Basic Heuristic)
131
- */
132
- export async function handleSentimentAnalysis(args) {
133
- try {
134
- let textToAnalyze = args.text || '';
135
- if (args.url || args.selector) {
136
- const page = getPageInstance();
137
- if (!page)
138
- throw new Error('Browser not initialized');
139
- if (args.url && page.url() !== args.url) {
140
- await page.goto(args.url, { waitUntil: 'domcontentloaded' });
141
- }
142
- if (args.selector) {
143
- textToAnalyze = await page.evaluate((sel) => document.querySelector(sel)?.textContent || '', args.selector);
144
- }
145
- else if (!textToAnalyze) {
146
- textToAnalyze = await page.evaluate(() => document.body.innerText);
147
- }
148
- }
149
- if (!textToAnalyze)
150
- throw new Error('No text to analyze');
151
- // Simple Bag of Words
152
- const positiveWords = ['good', 'great', 'awesome', 'excellent', 'happy', 'love', 'best', 'wonderful', 'amazing'];
153
- const negativeWords = ['bad', 'terrible', 'awful', 'worst', 'hate', 'sad', 'poor', 'disappointing', 'fail'];
154
- const lowerText = textToAnalyze.toLowerCase();
155
- let score = 0;
156
- let matchCount = 0;
157
- positiveWords.forEach(w => {
158
- const regex = new RegExp(`\\b${w}\\b`, 'g');
159
- const count = (lowerText.match(regex) || []).length;
160
- score += count;
161
- matchCount += count;
162
- });
163
- negativeWords.forEach(w => {
164
- const regex = new RegExp(`\\b${w}\\b`, 'g');
165
- const count = (lowerText.match(regex) || []).length;
166
- score -= count;
167
- matchCount += count;
168
- });
169
- let sentiment = 'Neutral';
170
- if (score > 0)
171
- sentiment = 'Positive';
172
- if (score < 0)
173
- sentiment = 'Negative';
174
- return {
175
- content: [{
176
- type: 'text',
177
- text: JSON.stringify({ sentiment, score, matchCount, analyzedLength: textToAnalyze.length }, null, 2)
178
- }]
179
- };
180
- }
181
- catch (error) {
182
- return { content: [{ type: 'text', text: `❌ Error: ${error.message}` }], isError: true };
183
- }
184
- }
185
- /**
186
- * Summary Generator - Generate summary of page content (Basic Truncation/Extraction)
187
- */
188
- export async function handleSummaryGenerator(args) {
189
- try {
190
- let textToSummary = args.text || '';
191
- if (args.url || args.selector) {
192
- const page = getPageInstance();
193
- if (!page)
194
- throw new Error('Browser not initialized');
195
- if (args.url && page.url() !== args.url) {
196
- await page.goto(args.url, { waitUntil: 'domcontentloaded' });
197
- }
198
- if (args.selector) {
199
- textToSummary = await page.evaluate((sel) => document.querySelector(sel)?.textContent || '', args.selector);
200
- }
201
- else if (!textToSummary) {
202
- // Heuristic: Get paragraphs
203
- textToSummary = await page.evaluate(() => {
204
- return Array.from(document.querySelectorAll('p')).map(p => p.textContent).join('\n\n');
205
- });
206
- }
207
- }
208
- if (!textToSummary)
209
- throw new Error('No text to summarize');
210
- // Basic Summary: First 5 sentences or maxLength
211
- const sentences = textToSummary.split(/[.!?]+/).filter(s => s.trim().length > 20);
212
- const summary = sentences.slice(0, 5).join('. ') + '.';
213
- const finalSummary = args.maxLength ? summary.slice(0, args.maxLength) : summary;
214
- return {
215
- content: [{
216
- type: 'text',
217
- text: JSON.stringify({ summary: finalSummary, originalLength: textToSummary.length }, null, 2)
218
- }]
219
- };
220
- }
221
- catch (error) {
222
- return { content: [{ type: 'text', text: `❌ Error: ${error.message}` }], isError: true };
223
- }
224
- }
225
- /**
226
- * Translation Support - Placeholder
227
- */
228
- export async function handleTranslationSupport(args) {
229
- return {
230
- content: [{
231
- type: 'text',
232
- text: `⚠️ Translation Support requires an external API (e.g., Google Translate, DeepL). This feature is defined but currently running in 'offline' mode. To implement, valid API keys would be required.\n\nInput extracted: ${args.text ? 'Yes' : 'No'}\nTarget Language: ${args.targetLanguage}`
233
- }]
234
- };
235
- }
@@ -5,82 +5,6 @@
5
5
  import { getCurrentPage } from '../browser-manager.js';
6
6
  import { validateWorkflow } from '../workflow-validation.js';
7
7
  import { withErrorHandling } from '../system-utils.js';
8
- /**
9
- * Bullet lists और numbered lists से data extract करता है
10
- */
11
- export async function handleExtractList(args) {
12
- return await withErrorHandling(async () => {
13
- validateWorkflow('extract_list', {
14
- requireBrowser: true,
15
- requirePage: true,
16
- });
17
- const page = getCurrentPage();
18
- const selector = args.selector || 'ul, ol';
19
- const includeNested = args.includeNested !== false;
20
- const maxItems = args.maxItems || 500;
21
- const listData = await page.evaluate(({ selector, includeNested, maxItems }) => {
22
- const lists = document.querySelectorAll(selector);
23
- const results = [];
24
- lists.forEach((list) => {
25
- const items = [];
26
- const listType = list.tagName.toLowerCase();
27
- let hasNested = false;
28
- const extractItems = (element, depth = 0) => {
29
- if (items.length >= maxItems)
30
- return;
31
- const children = Array.from(element.children);
32
- children.forEach((child) => {
33
- if (child.tagName.toLowerCase() === 'li') {
34
- const text = Array.from(child.childNodes)
35
- .filter((node) => node.nodeType === Node.TEXT_NODE)
36
- .map((node) => node.textContent?.trim())
37
- .filter((text) => text)
38
- .join(' ');
39
- if (text) {
40
- const indent = ' '.repeat(depth);
41
- items.push(`${indent}${text}`);
42
- }
43
- // Check for nested lists
44
- const nestedList = child.querySelector('ul, ol');
45
- if (nestedList && includeNested) {
46
- hasNested = true;
47
- extractItems(nestedList, depth + 1);
48
- }
49
- }
50
- });
51
- };
52
- extractItems(list);
53
- if (items.length > 0) {
54
- results.push({
55
- items,
56
- type: listType,
57
- nested: hasNested,
58
- count: items.length,
59
- });
60
- }
61
- });
62
- return results;
63
- }, { selector, includeNested, maxItems });
64
- if (listData.length === 0) {
65
- return {
66
- content: [
67
- {
68
- type: 'text',
69
- text: `❌ No lists found with selector "${selector}"`,
70
- },
71
- ],
72
- };
73
- }
74
- return {
75
- content: [
76
- {
77
- type: 'text',
78
- text: `✅ Extracted ${listData.length} list(s)\n\n${JSON.stringify(listData, null, 2)}`,
79
- },
80
- ],
81
- };
82
- }, 'Failed to extract list');
83
- }
84
8
  /**
85
9
  * Page में embedded JSON/API data खोजता और extract करता है
86
10
  */
@@ -46,46 +46,4 @@ export async function handleHTMLToText(args) {
46
46
  };
47
47
  }, 'Failed to convert HTML to text');
48
48
  }
49
- /**
50
- * Repeated data filter करता है
51
- */
52
- export async function handleDuplicateRemover(args) {
53
- return await withErrorHandling(async () => {
54
- const data = args.data;
55
- const uniqueKey = args.uniqueKey;
56
- let unique;
57
- if (uniqueKey) {
58
- // Remove duplicates based on specific key
59
- const seen = new Set();
60
- unique = data.filter((item) => {
61
- const value = item[uniqueKey];
62
- if (seen.has(value)) {
63
- return false;
64
- }
65
- seen.add(value);
66
- return true;
67
- });
68
- }
69
- else {
70
- // Remove duplicates based on entire object
71
- const seen = new Set();
72
- unique = data.filter((item) => {
73
- const serialized = JSON.stringify(item);
74
- if (seen.has(serialized)) {
75
- return false;
76
- }
77
- seen.add(serialized);
78
- return true;
79
- });
80
- }
81
- const removed = data.length - unique.length;
82
- return {
83
- content: [
84
- {
85
- type: 'text',
86
- text: `✅ Duplicates removed\n\nOriginal: ${data.length} items\nUnique: ${unique.length} items\nRemoved: ${removed} duplicates\n\n${JSON.stringify(unique, null, 2)}`,
87
- },
88
- ],
89
- };
90
- }, 'Failed to remove duplicates');
91
- }
49
+ // Duplicate Remover Arguments
@@ -1,76 +1,9 @@
1
1
  // @ts-nocheck
2
2
  import Ajv from 'ajv/dist/2020.js';
3
- import * as crypto from 'crypto';
4
3
  const ajv = new Ajv();
5
4
  /**
6
5
  * Data Deduplication - Remove duplicate entries from scraped data
7
6
  */
8
- export async function handleDataDeduplication(args) {
9
- const { data, uniqueKeys, fuzzyMatch = false, threshold = 0.9 } = args;
10
- try {
11
- if (!Array.isArray(data)) {
12
- throw new Error('Data must be an array');
13
- }
14
- const unique = [];
15
- const duplicates = [];
16
- const seen = new Set();
17
- data.forEach((item, index) => {
18
- let key;
19
- if (uniqueKeys && Array.isArray(uniqueKeys)) {
20
- // Create composite key from specified fields
21
- const keyParts = uniqueKeys.map(k => {
22
- const value = typeof item === 'object' ? item[k] : item;
23
- return String(value || '');
24
- });
25
- key = keyParts.join('|');
26
- }
27
- else {
28
- // Use entire object as key
29
- key = JSON.stringify(item);
30
- }
31
- if (fuzzyMatch) {
32
- // Normalize key for fuzzy matching
33
- key = key.toLowerCase().replace(/\s+/g, ' ').trim();
34
- }
35
- const hash = crypto.createHash('md5').update(key).digest('hex');
36
- if (seen.has(hash)) {
37
- duplicates.push({ item, index, hash });
38
- }
39
- else {
40
- seen.add(hash);
41
- unique.push(item);
42
- }
43
- });
44
- const dedupRate = ((duplicates.length / data.length) * 100).toFixed(2);
45
- let summary = `Data Deduplication Results:\n\nStatistics:\n- Original Items: ${data.length}\n- Unique Items: ${unique.length}\n- Duplicates Found: ${duplicates.length}\n- Deduplication Rate: ${dedupRate}%`;
46
- if (uniqueKeys) {
47
- summary += `\n- Unique Keys Used: ${uniqueKeys.join(', ')}`;
48
- }
49
- summary += `\n- Fuzzy Matching: ${fuzzyMatch ? 'Enabled' : 'Disabled'}`;
50
- if (duplicates.length > 0) {
51
- summary += `\n\nSample Duplicates (Top 5):\n${duplicates.slice(0, 5).map((d, i) => `${i + 1}. Index ${d.index}: ${JSON.stringify(d.item).substring(0, 100)}...`).join('\n')}`;
52
- }
53
- return {
54
- content: [
55
- {
56
- type: "text",
57
- text: summary
58
- }
59
- ]
60
- };
61
- }
62
- catch (error) {
63
- return {
64
- content: [
65
- {
66
- type: "text",
67
- text: `Data Deduplication Error: ${error.message}`
68
- }
69
- ],
70
- isError: true
71
- };
72
- }
73
- }
74
7
  /**
75
8
  * Missing Data Handler - Detect and handle missing data
76
9
  */
@@ -144,188 +77,6 @@ export async function handleDataTypeValidator(args) {
144
77
  };
145
78
  }
146
79
  }
147
- /**
148
- * Outlier Detection - Detect outliers in numerical data
149
- */
150
- export async function handleOutlierDetection(args) {
151
- const { data, field, method = 'iqr', threshold = 1.5 } = args;
152
- try {
153
- if (!Array.isArray(data)) {
154
- throw new Error('Data must be an array');
155
- }
156
- // Extract numerical values
157
- const values = data
158
- .map(item => {
159
- const value = field ? item[field] : item;
160
- return typeof value === 'number' ? value : parseFloat(value);
161
- })
162
- .filter(v => !isNaN(v));
163
- if (values.length === 0) {
164
- throw new Error('No valid numerical values found');
165
- }
166
- let outliers = [];
167
- let stats = {};
168
- // Sort values
169
- const sorted = [...values].sort((a, b) => a - b);
170
- // Calculate statistics
171
- const mean = values.reduce((a, b) => a + b, 0) / values.length;
172
- const variance = values.reduce((a, b) => a + Math.pow(b - mean, 2), 0) / values.length;
173
- const stdDev = Math.sqrt(variance);
174
- const q1Index = Math.floor(sorted.length * 0.25);
175
- const q3Index = Math.floor(sorted.length * 0.75);
176
- const q1 = sorted[q1Index];
177
- const q3 = sorted[q3Index];
178
- const iqr = q3 - q1;
179
- stats = {
180
- count: values.length,
181
- min: sorted[0],
182
- max: sorted[sorted.length - 1],
183
- mean: mean.toFixed(2),
184
- median: sorted[Math.floor(sorted.length / 2)],
185
- stdDev: stdDev.toFixed(2),
186
- q1,
187
- q3,
188
- iqr: iqr.toFixed(2)
189
- };
190
- // Detect outliers based on method
191
- if (method === 'iqr') {
192
- const lowerBound = q1 - threshold * iqr;
193
- const upperBound = q3 + threshold * iqr;
194
- data.forEach((item, index) => {
195
- const value = field ? item[field] : item;
196
- const numValue = typeof value === 'number' ? value : parseFloat(value);
197
- if (!isNaN(numValue) && (numValue < lowerBound || numValue > upperBound)) {
198
- outliers.push({
199
- item,
200
- index,
201
- value: numValue,
202
- reason: numValue < lowerBound ? 'below lower bound' : 'above upper bound',
203
- bounds: { lower: lowerBound.toFixed(2), upper: upperBound.toFixed(2) }
204
- });
205
- }
206
- });
207
- }
208
- else if (method === 'zscore') {
209
- data.forEach((item, index) => {
210
- const value = field ? item[field] : item;
211
- const numValue = typeof value === 'number' ? value : parseFloat(value);
212
- if (!isNaN(numValue)) {
213
- const zscore = (numValue - mean) / stdDev;
214
- if (Math.abs(zscore) > threshold) {
215
- outliers.push({
216
- item,
217
- index,
218
- value: numValue,
219
- zscore: zscore.toFixed(2),
220
- reason: `zscore ${zscore > 0 ? 'above' : 'below'} threshold`
221
- });
222
- }
223
- }
224
- });
225
- }
226
- const outlierPercentage = ((outliers.length / data.length) * 100).toFixed(2);
227
- let summary = `Outlier Detection Results:\n\nMethod: ${method}\nThreshold: ${threshold}${field ? `\nField Analyzed: ${field}` : ''}\n\nStatistics:\n- Count: ${stats.count}\n- Min: ${stats.min}\n- Max: ${stats.max}\n- Mean: ${stats.mean}\n- Median: ${stats.median}\n- Std Dev: ${stats.stdDev}\n- Q1: ${stats.q1}\n- Q3: ${stats.q3}\n- IQR: ${stats.iqr}`;
228
- summary += `\n\nOutliers:\n- Count: ${outliers.length}\n- Percentage: ${outlierPercentage}%`;
229
- if (outliers.length > 0) {
230
- summary += `\n\nOutlier Samples (Top 10):\n${outliers.slice(0, 10).map((o, i) => {
231
- return `${i + 1}. Index ${o.index}: Value=${o.value}, Reason: ${o.reason}${o.zscore ? `, Z-score=${o.zscore}` : ''}${o.bounds ? `, Bounds=[${o.bounds.lower}, ${o.bounds.upper}]` : ''}`;
232
- }).join('\n')}`;
233
- }
234
- return {
235
- content: [
236
- {
237
- type: "text",
238
- text: summary
239
- }
240
- ]
241
- };
242
- }
243
- catch (error) {
244
- return {
245
- content: [
246
- {
247
- type: "text",
248
- text: `Outlier Detection Error: ${error.message}`
249
- }
250
- ],
251
- isError: true
252
- };
253
- }
254
- }
255
80
  /**
256
81
  * Consistency Checker - Check data consistency across fields
257
82
  */
258
- export async function handleConsistencyChecker(args) {
259
- const { data, rules } = args;
260
- try {
261
- if (!Array.isArray(data)) {
262
- throw new Error('Data must be an array');
263
- }
264
- if (!rules || !Array.isArray(rules)) {
265
- if (!rules)
266
- return { content: [{ type: "text", text: "No rules provided. Pass." }] };
267
- throw new Error('Rules must be an array');
268
- }
269
- const report = {
270
- totalItems: data.length,
271
- passedItems: 0,
272
- failedItems: 0,
273
- failures: []
274
- };
275
- data.forEach((item, index) => {
276
- let itemPassed = true;
277
- const itemFailures = [];
278
- rules.forEach((rule) => {
279
- try {
280
- if (rule.type === 'dependency') {
281
- if (item[rule.field] && !item[rule.dependentField]) {
282
- itemPassed = false;
283
- itemFailures.push(`Field '${rule.field}' requires '${rule.dependentField}'`);
284
- }
285
- }
286
- else if (rule.type === 'value_match') {
287
- if (item[rule.field] === rule.value && item[rule.targetField] !== rule.targetValue) {
288
- itemPassed = false;
289
- itemFailures.push(`When '${rule.field}' is '${rule.value}', '${rule.targetField}' must be '${rule.targetValue}'`);
290
- }
291
- }
292
- }
293
- catch (e) {
294
- itemPassed = false;
295
- // @ts-ignore
296
- itemFailures.push(`Rule execution error: ${e.message}`);
297
- }
298
- });
299
- if (itemPassed) {
300
- report.passedItems++;
301
- }
302
- else {
303
- report.failedItems++;
304
- report.failures.push({
305
- index,
306
- item,
307
- errors: itemFailures
308
- });
309
- }
310
- });
311
- return {
312
- content: [
313
- {
314
- type: "text",
315
- text: `Consistency Check Results:\nTotal: ${report.totalItems}\nPassed: ${report.passedItems}\nFailed: ${report.failedItems}\n\nFailures:\n${JSON.stringify(report.failures, null, 2)}`
316
- }
317
- ]
318
- };
319
- }
320
- catch (error) {
321
- return {
322
- content: [
323
- {
324
- type: "text",
325
- text: `Consistency Checker Error: ${error.message}`
326
- }
327
- ],
328
- isError: true
329
- };
330
- }
331
- }
@@ -49,81 +49,6 @@ export async function handleShadowDOMExtractor(args) {
49
49
  /**
50
50
  * Cookie Manager - Manage cookies
51
51
  */
52
- export async function handleCookieManager(args) {
53
- return await withErrorHandling(async () => {
54
- validateWorkflow('cookie_manager', {
55
- requireBrowser: true,
56
- requirePage: true,
57
- });
58
- const page = getCurrentPage();
59
- const action = args.action || 'get'; // get, set, delete, clear
60
- if (action === 'get') {
61
- const cookies = await page.cookies();
62
- return {
63
- content: [{
64
- type: 'text',
65
- text: `✅ Retrieved ${cookies.length} cookies\n\n${JSON.stringify(cookies, null, 2)}`,
66
- }],
67
- };
68
- }
69
- if (action === 'set') {
70
- const cookie = args.cookie;
71
- if (!cookie || !cookie.name || !cookie.value) {
72
- throw new Error('Cookie name and value are required');
73
- }
74
- await page.setCookie({
75
- name: cookie.name,
76
- value: cookie.value,
77
- domain: cookie.domain || new URL(page.url()).hostname,
78
- path: cookie.path || '/',
79
- expires: cookie.expires,
80
- httpOnly: cookie.httpOnly || false,
81
- secure: cookie.secure || false,
82
- sameSite: cookie.sameSite || 'Lax',
83
- });
84
- return {
85
- content: [{
86
- type: 'text',
87
- text: `✅ Cookie set: ${cookie.name} = ${cookie.value}`,
88
- }],
89
- };
90
- }
91
- if (action === 'delete') {
92
- const cookieName = args.cookieName;
93
- if (!cookieName) {
94
- throw new Error('Cookie name is required');
95
- }
96
- const cookies = await page.cookies();
97
- const cookieToDelete = cookies.find(c => c.name === cookieName);
98
- if (cookieToDelete) {
99
- await page.deleteCookie(cookieToDelete);
100
- return {
101
- content: [{
102
- type: 'text',
103
- text: `✅ Cookie deleted: ${cookieName}`,
104
- }],
105
- };
106
- }
107
- return {
108
- content: [{
109
- type: 'text',
110
- text: `⚠️ Cookie not found: ${cookieName}`,
111
- }],
112
- };
113
- }
114
- if (action === 'clear') {
115
- const cookies = await page.cookies();
116
- await Promise.all(cookies.map(cookie => page.deleteCookie(cookie)));
117
- return {
118
- content: [{
119
- type: 'text',
120
- text: `✅ Cleared all ${cookies.length} cookies`,
121
- }],
122
- };
123
- }
124
- throw new Error(`Unknown action: ${action}`);
125
- }, 'Failed to manage cookies');
126
- }
127
52
  /**
128
53
  * Session Persistence - Save and restore browser session
129
54
  */
@@ -1,8 +1,6 @@
1
1
  // Monitoring & Reporting Module
2
2
  // Progress tracking, error logging, success rate reporting, metrics
3
3
  // @ts-nocheck
4
- import { getCurrentPage } from '../browser-manager.js';
5
- import { validateWorkflow } from '../workflow-validation.js';
6
4
  import { withErrorHandling } from '../system-utils.js';
7
5
  // Global monitoring state
8
6
  const monitoringState = {
@@ -116,87 +114,6 @@ export async function handleProgressTracker(args) {
116
114
  /**
117
115
  * Data Quality Metrics - Report data quality metrics
118
116
  */
119
- export async function handleDataQualityMetrics(args) {
120
- return await withErrorHandling(async () => {
121
- validateWorkflow('data_quality_metrics', {
122
- requireBrowser: true,
123
- requirePage: true,
124
- });
125
- const page = getCurrentPage();
126
- const data = args.data || [];
127
- // Calculate metrics
128
- const metrics = {
129
- totalRecords: data.length,
130
- completeRecords: 0,
131
- incompleteRecords: 0,
132
- emptyFields: 0,
133
- duplicates: 0,
134
- dataTypes: {},
135
- fieldCompleteness: {},
136
- };
137
- if (data.length === 0) {
138
- return {
139
- content: [{
140
- type: 'text',
141
- text: `ℹ️ No data provided for quality metrics`,
142
- }],
143
- };
144
- }
145
- // Analyze data quality
146
- const seenRecords = new Set();
147
- const allFields = new Set();
148
- data.forEach((record) => {
149
- const recordStr = JSON.stringify(record);
150
- // Check for duplicates
151
- if (seenRecords.has(recordStr)) {
152
- metrics.duplicates++;
153
- }
154
- else {
155
- seenRecords.add(recordStr);
156
- }
157
- // Collect all fields
158
- Object.keys(record).forEach(key => allFields.add(key));
159
- // Check completeness
160
- let hasAllFields = true;
161
- Object.values(record).forEach(value => {
162
- if (value === null || value === undefined || value === '') {
163
- metrics.emptyFields++;
164
- hasAllFields = false;
165
- }
166
- });
167
- if (hasAllFields) {
168
- metrics.completeRecords++;
169
- }
170
- else {
171
- metrics.incompleteRecords++;
172
- }
173
- });
174
- // Field completeness
175
- allFields.forEach(field => {
176
- const nonEmptyCount = data.filter((record) => {
177
- const value = record[field];
178
- return value !== null && value !== undefined && value !== '';
179
- }).length;
180
- metrics.fieldCompleteness[field] = ((nonEmptyCount / data.length) * 100).toFixed(2) + '%';
181
- });
182
- // Data type analysis
183
- allFields.forEach(field => {
184
- const types = new Set();
185
- data.forEach((record) => {
186
- const value = record[field];
187
- types.add(typeof value);
188
- });
189
- metrics.dataTypes[field] = Array.from(types).join(', ');
190
- });
191
- const qualityScore = ((metrics.completeRecords / metrics.totalRecords) * 100).toFixed(2);
192
- return {
193
- content: [{
194
- type: 'text',
195
- text: `✅ Data Quality Metrics\n\nTotal Records: ${metrics.totalRecords}\nComplete Records: ${metrics.completeRecords}\nIncomplete Records: ${metrics.incompleteRecords}\nDuplicates: ${metrics.duplicates}\nEmpty Fields: ${metrics.emptyFields}\n\nQuality Score: ${qualityScore}%\n\nField Completeness:\n${JSON.stringify(metrics.fieldCompleteness, null, 2)}\n\nData Types:\n${JSON.stringify(metrics.dataTypes, null, 2)}`,
196
- }],
197
- };
198
- }, 'Failed data quality metrics');
199
- }
200
117
  /**
201
118
  * Performance Monitor - Monitor browser and page performance
202
119
  */
@@ -2,64 +2,10 @@
2
2
  import { getPageInstance } from '../browser-manager.js';
3
3
  import * as fs from 'fs/promises';
4
4
  import * as path from 'path';
5
- import pixelmatch from 'pixelmatch';
6
- import { PNG } from 'pngjs';
7
5
  import { sleep } from '../system-utils.js';
8
6
  /**
9
7
  * Full Page Screenshot - Capture entire page
10
8
  */
11
- export async function handleFullPageScreenshot(args) {
12
- const { url, outputPath, format = 'png', quality = 90, fullPage = true } = args;
13
- try {
14
- const page = getPageInstance();
15
- if (!page) {
16
- throw new Error('Browser not initialized. Call browser_init first.');
17
- }
18
- if (url && page.url() !== url) {
19
- await page.goto(url, { waitUntil: 'networkidle2', timeout: 30000 });
20
- }
21
- // Ensure output directory exists
22
- if (outputPath) {
23
- const dir = path.dirname(outputPath);
24
- await fs.mkdir(dir, { recursive: true });
25
- }
26
- const screenshotOptions = {
27
- path: outputPath,
28
- type: format,
29
- fullPage
30
- };
31
- if (format === 'jpeg') {
32
- screenshotOptions.quality = quality;
33
- }
34
- await page.screenshot(screenshotOptions);
35
- // Get file stats if saved
36
- let fileSize = 0;
37
- if (outputPath) {
38
- const stats = await fs.stat(outputPath);
39
- fileSize = stats.size;
40
- }
41
- const resultText = `✅ Screenshot captured successfully\n\nPath: ${outputPath}\nFormat: ${format}\nFull Page: ${fullPage}\nFile Size: ${(fileSize / 1024).toFixed(2)} KB\nTimestamp: ${new Date().toISOString()}`;
42
- return {
43
- content: [
44
- {
45
- type: 'text',
46
- text: resultText,
47
- },
48
- ],
49
- };
50
- }
51
- catch (error) {
52
- return {
53
- content: [
54
- {
55
- type: 'text',
56
- text: `❌ Screenshot failed: ${error.message}`,
57
- },
58
- ],
59
- isError: true,
60
- };
61
- }
62
- }
63
9
  /**
64
10
  * Element Screenshot - Capture specific element
65
11
  */
@@ -205,63 +151,3 @@ export async function handleVideoRecording(args) {
205
151
  };
206
152
  }
207
153
  }
208
- /**
209
- * Visual Comparison - Compare two screenshots
210
- */
211
- export async function handleVisualComparison(args) {
212
- const { image1Path, image2Path, diffOutputPath, threshold = 0.1 } = args;
213
- try {
214
- if (!image1Path || !image2Path) {
215
- throw new Error('Both image paths are required');
216
- }
217
- // Read images
218
- const img1Data = await fs.readFile(image1Path);
219
- const img2Data = await fs.readFile(image2Path);
220
- const img1 = PNG.sync.read(img1Data);
221
- const img2 = PNG.sync.read(img2Data);
222
- // Check if dimensions match
223
- if (img1.width !== img2.width || img1.height !== img2.height) {
224
- return {
225
- content: [
226
- {
227
- type: "text",
228
- text: `Image dimensions do not match:\n- Image 1: ${img1.width}x${img1.height}\n- Image 2: ${img2.width}x${img2.height}`
229
- }
230
- ],
231
- isError: true
232
- };
233
- }
234
- // Create diff image
235
- const diff = new PNG({ width: img1.width, height: img1.height });
236
- // Compare images
237
- const numDiffPixels = pixelmatch(img1.data, img2.data, diff.data, img1.width, img1.height, { threshold });
238
- // Save diff image if path provided
239
- if (diffOutputPath) {
240
- const dir = path.dirname(diffOutputPath);
241
- await fs.mkdir(dir, { recursive: true });
242
- await fs.writeFile(diffOutputPath, PNG.sync.write(diff));
243
- }
244
- const totalPixels = img1.width * img1.height;
245
- const diffPercentage = (numDiffPixels / totalPixels) * 100;
246
- const similarity = ((1 - (numDiffPixels / totalPixels)) * 100).toFixed(2);
247
- return {
248
- content: [
249
- {
250
- type: "text",
251
- text: `Visual Comparison Results:\n- Identical: ${numDiffPixels === 0 ? 'Yes' : 'No'}\n- Similarity: ${similarity}%\n- Different Pixels: ${numDiffPixels} (${diffPercentage.toFixed(2)}%)\n- Total Pixels: ${totalPixels}\n- Image Dimensions: ${img1.width}x${img1.height}\n- Threshold: ${threshold}${diffOutputPath ? `\n- Diff Image Saved: ${diffOutputPath}` : ''}`
252
- }
253
- ]
254
- };
255
- }
256
- catch (error) {
257
- return {
258
- content: [
259
- {
260
- type: "text",
261
- text: `Visual Comparison Error: ${error.message}`
262
- }
263
- ],
264
- isError: true
265
- };
266
- }
267
- }
package/dist/index.js CHANGED
@@ -26,29 +26,29 @@ import { handleClick, handleType, handleSolveCaptcha, handleRandomScroll, } from
26
26
  import { handleGetContent, handleFindSelector, } from "./handlers/content-handlers.js";
27
27
  import { handleSaveContentAsMarkdown } from "./handlers/file-handlers.js";
28
28
  // Import new data extraction handlers
29
- import { handleExtractList, handleExtractJSON, handleScrapeMetaTags, handleExtractSchema, } from "./handlers/data-extraction-handlers.js";
29
+ import { handleExtractJSON, handleScrapeMetaTags, handleExtractSchema, } from "./handlers/data-extraction-handlers.js";
30
30
  // Import multi-element handlers
31
31
  import { handleBatchElementScraper, handleNestedDataExtraction, handleAttributeHarvester, handleLinkHarvester, handleMediaExtractor, } from "./handlers/multi-element-handlers.js";
32
32
  // Import pagination handlers
33
33
  import { handleMultiPageScraper, handleBreadcrumbNavigator, } from "./handlers/pagination-handlers.js";
34
34
  // Import data processing handlers
35
- import { handleHTMLToText, handleDuplicateRemover, } from "./handlers/data-processing-handlers.js";
35
+ import { handleHTMLToText, } from "./handlers/data-processing-handlers.js";
36
36
  // Import AI-powered handlers
37
37
  import { handleSmartSelectorGenerator, handleContentClassification, } from "./handlers/ai-powered-handlers.js";
38
38
  // Import search & filter handlers
39
39
  import { handleKeywordSearch, handleRegexPatternMatcher, handleXPathSupport, handleAdvancedCSSSelectors, handleVisualElementFinder, } from "./handlers/search-filter-handlers.js";
40
40
  // Import data quality handlers
41
- import { handleDataDeduplication, handleDataTypeValidator, handleOutlierDetection, } from "./handlers/data-quality-handlers.js";
41
+ import { handleDataTypeValidator, } from "./handlers/data-quality-handlers.js";
42
42
  // Import captcha handlers
43
43
  import { handleOCREngine, handleAudioCaptchaSolver, handlePuzzleCaptchaHandler, } from "./handlers/captcha-handlers.js";
44
44
  // Import visual tools handlers
45
- import { handleFullPageScreenshot, handleElementScreenshot, handleVideoRecording, handleVisualComparison, } from "./handlers/visual-tools-handlers.js";
45
+ import { handleElementScreenshot, handleVideoRecording, } from "./handlers/visual-tools-handlers.js";
46
46
  // Import smart data extractors
47
47
  import { handleHtmlElementsExtractor, handleTagsFinder, handleLinksFinder, handleXpathLinks, handleAjaxExtractor, handleFetchXHR, handleNetworkRecorder, handleRegexPatternFinder, handleIframeExtractor, handleEmbedPageExtractor, handleImageExtractorAdvanced, handleVideoSourceExtractor, handleUrlRedirectTracer, handleUserAgentExtractor, } from "./handlers/smart-data-extractors.js";
48
48
  // Import dynamic session handlers
49
- import { handleShadowDOMExtractor, handleCookieManager, handleFormAutoFill, handleAjaxContentWaiter, } from "./handlers/dynamic-session-handlers.js";
49
+ import { handleShadowDOMExtractor, handleFormAutoFill, handleAjaxContentWaiter, } from "./handlers/dynamic-session-handlers.js";
50
50
  // Import monitoring & reporting handlers
51
- import { handleProgressTracker, handleDataQualityMetrics, } from "./handlers/monitoring-reporting-handlers.js";
51
+ import { handleProgressTracker, } from "./handlers/monitoring-reporting-handlers.js";
52
52
  // Import advanced video & media handlers
53
53
  import { handleVideoLinkFinder, handleVideoDownloadButton, handleVideoPlayPushSource, handleVideoPlayButtonClick, } from "./handlers/advanced-video-media-handlers.js";
54
54
  // Import advanced extraction handlers (Ad-bypass & Obfuscation)
@@ -139,9 +139,6 @@ export async function executeToolByName(name, args) {
139
139
  result = await handleSaveContentAsMarkdown(args);
140
140
  break;
141
141
  // Smart Data Extractors
142
- case TOOL_NAMES.EXTRACT_LIST:
143
- result = await handleExtractList(args || {});
144
- break;
145
142
  case TOOL_NAMES.EXTRACT_JSON:
146
143
  result = await handleExtractJSON(args || {});
147
144
  break;
@@ -180,9 +177,6 @@ export async function executeToolByName(name, args) {
180
177
  case TOOL_NAMES.HTML_TO_TEXT:
181
178
  result = await handleHTMLToText(args);
182
179
  break;
183
- case TOOL_NAMES.DUPLICATE_REMOVER:
184
- result = await handleDuplicateRemover(args);
185
- break;
186
180
  // AI-Powered Features
187
181
  case TOOL_NAMES.SMART_SELECTOR_GENERATOR:
188
182
  result = await handleSmartSelectorGenerator(args);
@@ -207,15 +201,9 @@ export async function executeToolByName(name, args) {
207
201
  result = await handleVisualElementFinder(args);
208
202
  break;
209
203
  // Data Quality & Validation
210
- case TOOL_NAMES.DATA_DEDUPLICATION:
211
- result = await handleDataDeduplication(args);
212
- break;
213
204
  case TOOL_NAMES.DATA_TYPE_VALIDATOR:
214
205
  result = await handleDataTypeValidator(args);
215
206
  break;
216
- case TOOL_NAMES.OUTLIER_DETECTION:
217
- result = await handleOutlierDetection(args);
218
- break;
219
207
  // Advanced Captcha Handling
220
208
  case TOOL_NAMES.OCR_ENGINE:
221
209
  result = await handleOCREngine(args);
@@ -227,18 +215,12 @@ export async function executeToolByName(name, args) {
227
215
  result = await handlePuzzleCaptchaHandler(args);
228
216
  break;
229
217
  // Screenshot & Visual Tools
230
- case TOOL_NAMES.FULL_PAGE_SCREENSHOT:
231
- result = await handleFullPageScreenshot(args);
232
- break;
233
218
  case TOOL_NAMES.ELEMENT_SCREENSHOT:
234
219
  result = await handleElementScreenshot(args);
235
220
  break;
236
221
  case TOOL_NAMES.VIDEO_RECORDING:
237
222
  result = await handleVideoRecording(args);
238
223
  break;
239
- case TOOL_NAMES.VISUAL_COMPARISON:
240
- result = await handleVisualComparison(args);
241
- break;
242
224
  // Smart Data Extractors (Advanced)
243
225
  case "html_elements_extractor":
244
226
  result = await handleHtmlElementsExtractor(args || {});
@@ -286,9 +268,6 @@ export async function executeToolByName(name, args) {
286
268
  case "shadow_dom_extractor":
287
269
  result = await handleShadowDOMExtractor(args || {});
288
270
  break;
289
- case "cookie_manager":
290
- result = await handleCookieManager(args);
291
- break;
292
271
  case "form_auto_fill":
293
272
  result = await handleFormAutoFill(args);
294
273
  break;
@@ -299,9 +278,6 @@ export async function executeToolByName(name, args) {
299
278
  case "progress_tracker":
300
279
  result = await handleProgressTracker(args || {});
301
280
  break;
302
- case "data_quality_metrics":
303
- result = await handleDataQualityMetrics(args || {});
304
- break;
305
281
  // Advanced Video & Media Download Tools
306
282
  case "video_link_finder":
307
283
  result = await handleVideoLinkFinder(args || {});
@@ -331,18 +331,6 @@ export const TOOLS = [
331
331
  },
332
332
  },
333
333
  // Smart Data Extractors
334
- {
335
- name: 'extract_list',
336
- description: 'Extract data from bullet lists and numbered lists',
337
- inputSchema: {
338
- type: 'object',
339
- properties: {
340
- selector: { type: 'string', default: 'ul, ol' },
341
- includeNested: { type: 'boolean', default: true },
342
- maxItems: { type: 'number', default: 500 },
343
- },
344
- },
345
- },
346
334
  {
347
335
  name: 'extract_json',
348
336
  description: 'Extract embedded JSON/API data from the page',
@@ -483,18 +471,6 @@ export const TOOLS = [
483
471
  },
484
472
  },
485
473
  // Data Validation Tools
486
- {
487
- name: 'duplicate_remover',
488
- description: 'Remove duplicate items from an array',
489
- inputSchema: {
490
- type: 'object',
491
- properties: {
492
- data: { type: 'array' },
493
- uniqueKey: { type: 'string' },
494
- },
495
- required: ['data'],
496
- },
497
- },
498
474
  // AI-Powered Features (5 tools)
499
475
  {
500
476
  name: 'smart_selector_generator',
@@ -593,20 +569,6 @@ export const TOOLS = [
593
569
  },
594
570
  },
595
571
  // Data Quality & Validation (5 tools)
596
- {
597
- name: 'data_deduplication',
598
- description: 'Remove duplicate entries from scraped data',
599
- inputSchema: {
600
- type: 'object',
601
- properties: {
602
- data: { type: 'array' },
603
- uniqueKeys: { type: 'array', items: { type: 'string' } },
604
- fuzzyMatch: { type: 'boolean', default: false },
605
- threshold: { type: 'number', default: 0.9 },
606
- },
607
- required: ['data'],
608
- },
609
- },
610
572
  {
611
573
  name: 'data_type_validator',
612
574
  description: 'Validate data types against JSON schema',
@@ -619,32 +581,6 @@ export const TOOLS = [
619
581
  required: ['data', 'schema'],
620
582
  },
621
583
  },
622
- {
623
- name: 'outlier_detection',
624
- description: 'Detect outliers in numerical data',
625
- inputSchema: {
626
- type: 'object',
627
- properties: {
628
- data: { type: 'array' },
629
- field: { type: 'string', description: 'Field to analyze' },
630
- method: { type: 'string', enum: ['iqr', 'zscore'], default: 'iqr' },
631
- threshold: { type: 'number', default: 1.5 },
632
- },
633
- required: ['data'],
634
- },
635
- },
636
- {
637
- name: 'consistency_checker',
638
- description: 'Check data consistency across fields',
639
- inputSchema: {
640
- type: 'object',
641
- properties: {
642
- data: { type: 'array' },
643
- rules: { type: 'array', description: 'Validation rules' },
644
- },
645
- required: ['data', 'rules'],
646
- },
647
- },
648
584
  // Advanced Captcha Handling (3 tools)
649
585
  {
650
586
  name: 'ocr_engine',
@@ -687,21 +623,6 @@ export const TOOLS = [
687
623
  },
688
624
  },
689
625
  // Screenshot & Visual Tools (5 tools)
690
- {
691
- name: 'full_page_screenshot',
692
- description: 'Capture entire page screenshot',
693
- inputSchema: {
694
- type: 'object',
695
- properties: {
696
- url: { type: 'string' },
697
- outputPath: { type: 'string' },
698
- format: { type: 'string', enum: ['png', 'jpeg'], default: 'png' },
699
- quality: { type: 'number', default: 90 },
700
- fullPage: { type: 'boolean', default: true },
701
- },
702
- required: ['outputPath'],
703
- },
704
- },
705
626
  {
706
627
  name: 'element_screenshot',
707
628
  description: 'Capture screenshot of specific element',
@@ -730,20 +651,6 @@ export const TOOLS = [
730
651
  required: ['outputPath'],
731
652
  },
732
653
  },
733
- {
734
- name: 'visual_comparison',
735
- description: 'Compare two screenshots',
736
- inputSchema: {
737
- type: 'object',
738
- properties: {
739
- image1Path: { type: 'string' },
740
- image2Path: { type: 'string' },
741
- diffOutputPath: { type: 'string' },
742
- threshold: { type: 'number', default: 0.1 },
743
- },
744
- required: ['image1Path', 'image2Path'],
745
- },
746
- },
747
654
  // Smart Data Extractors (Advanced)
748
655
  {
749
656
  name: 'html_elements_extractor',
@@ -898,18 +805,6 @@ export const TOOLS = [
898
805
  },
899
806
  },
900
807
  },
901
- {
902
- name: 'cookie_manager',
903
- description: 'Manage cookies (get, set, delete, clear)',
904
- inputSchema: {
905
- type: 'object',
906
- properties: {
907
- action: { type: 'string', enum: ['get', 'set', 'delete', 'clear'], default: 'get' },
908
- cookie: { type: 'object' },
909
- cookieName: { type: 'string' },
910
- },
911
- },
912
- },
913
808
  {
914
809
  name: 'form_auto_fill',
915
810
  description: 'Automatically fill form fields',
@@ -950,16 +845,6 @@ export const TOOLS = [
950
845
  },
951
846
  },
952
847
  },
953
- {
954
- name: 'data_quality_metrics',
955
- description: 'Report data quality metrics',
956
- inputSchema: {
957
- type: 'object',
958
- properties: {
959
- data: { type: 'array' },
960
- },
961
- },
962
- },
963
848
  // Advanced Video & Media Download Tools
964
849
  {
965
850
  name: 'video_link_finder',
@@ -1055,43 +940,6 @@ export const TOOLS = [
1055
940
  },
1056
941
  },
1057
942
  },
1058
- {
1059
- name: 'sentiment_analysis',
1060
- description: 'Analyze the sentiment of text or page content',
1061
- inputSchema: {
1062
- type: 'object',
1063
- properties: {
1064
- text: { type: 'string', description: 'Text to analyze' },
1065
- url: { type: 'string', description: 'URL to analyze' },
1066
- selector: { type: 'string', description: 'Selector to extract text from' }
1067
- }
1068
- }
1069
- },
1070
- {
1071
- name: 'summary_generator',
1072
- description: 'Generate a summary of text or page content',
1073
- inputSchema: {
1074
- type: 'object',
1075
- properties: {
1076
- text: { type: 'string', description: 'Text to summarize' },
1077
- url: { type: 'string', description: 'URL to summarize' },
1078
- selector: { type: 'string', description: 'Selector to extract text from' },
1079
- maxLength: { type: 'number', description: 'Maximum length of summary' }
1080
- }
1081
- }
1082
- },
1083
- {
1084
- name: 'translation_support',
1085
- description: 'Detect language and translate text',
1086
- inputSchema: {
1087
- type: 'object',
1088
- properties: {
1089
- text: { type: 'string', description: 'Text to translate' },
1090
- url: { type: 'string', description: 'URL to translate content from' },
1091
- targetLanguage: { type: 'string', description: 'Target language code (e.g. "es", "fr")' }
1092
- }
1093
- }
1094
- },
1095
943
  // Phase 3: Media & Video Tools
1096
944
  {
1097
945
  name: 'video_source_extractor',
@@ -1148,8 +996,6 @@ export const TOOL_NAMES = {
1148
996
  RANDOM_SCROLL: 'random_scroll',
1149
997
  FIND_SELECTOR: 'find_selector',
1150
998
  SAVE_CONTENT_AS_MARKDOWN: 'save_content_as_markdown',
1151
- // Smart Data Extractors
1152
- EXTRACT_LIST: 'extract_list',
1153
999
  EXTRACT_JSON: 'extract_json',
1154
1000
  SCRAPE_META_TAGS: 'scrape_meta_tags',
1155
1001
  EXTRACT_SCHEMA: 'extract_schema',
@@ -1178,13 +1024,9 @@ export const TOOL_NAMES = {
1178
1024
  BREADCRUMB_NAVIGATOR: 'breadcrumb_navigator',
1179
1025
  // Data Processing
1180
1026
  HTML_TO_TEXT: 'html_to_text',
1181
- DUPLICATE_REMOVER: 'duplicate_remover',
1182
1027
  // AI-Powered Features
1183
1028
  SMART_SELECTOR_GENERATOR: 'smart_selector_generator',
1184
1029
  CONTENT_CLASSIFICATION: 'content_classification',
1185
- SENTIMENT_ANALYSIS: 'sentiment_analysis',
1186
- SUMMARY_GENERATOR: 'summary_generator',
1187
- TRANSLATION_SUPPORT: 'translation_support',
1188
1030
  // Phase 3: Media & Video
1189
1031
  VIDEO_SOURCE_EXTRACTOR: 'video_source_extractor',
1190
1032
  VIDEO_PLAYER_FINDER: 'video_player_finder',
@@ -1196,18 +1038,14 @@ export const TOOL_NAMES = {
1196
1038
  ADVANCED_CSS_SELECTORS: 'advanced_css_selectors',
1197
1039
  VISUAL_ELEMENT_FINDER: 'visual_element_finder',
1198
1040
  // Data Quality & Validation
1199
- DATA_DEDUPLICATION: 'data_deduplication',
1200
1041
  DATA_TYPE_VALIDATOR: 'data_type_validator',
1201
- OUTLIER_DETECTION: 'outlier_detection',
1202
1042
  // Advanced Captcha Handling
1203
1043
  OCR_ENGINE: 'ocr_engine',
1204
1044
  AUDIO_CAPTCHA_SOLVER: 'audio_captcha_solver',
1205
1045
  PUZZLE_CAPTCHA_HANDLER: 'puzzle_captcha_handler',
1206
1046
  // Screenshot & Visual Tools
1207
- FULL_PAGE_SCREENSHOT: 'full_page_screenshot',
1208
1047
  ELEMENT_SCREENSHOT: 'element_screenshot',
1209
1048
  VIDEO_RECORDING: 'video_recording',
1210
- VISUAL_COMPARISON: 'visual_comparison',
1211
1049
  };
1212
1050
  // Tool categories for organization
1213
1051
  export const TOOL_CATEGORIES = {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "brave-real-browser-mcp-server",
3
- "version": "2.15.3",
3
+ "version": "2.15.5",
4
4
  "description": "Universal AI IDE MCP Server - Auto-detects and supports all AI IDEs (Claude Desktop, Cursor, Windsurf, Cline, Zed, VSCode, Qoder AI, etc.) with Brave browser automation",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",