Dumpling AI MCP Server

1# Dumpling AI MCP Server
2 
3A Model Context Protocol (MCP) server implementation that integrates with Dumpling AI for data scraping, content processing, knowledge management, AI agents, and code execution capabilities.
4 
5[![smithery badge](https://smithery.ai/badge/@Dumpling-AI/mcp-server-dumplingai)](https://smithery.ai/server/@Dumpling-AI/mcp-server-dumplingai)
6 
7## Features
8 
9- Complete integration with all Dumpling AI API endpoints
10- Data APIs for YouTube transcripts, search, autocomplete, maps, places, news, and reviews
11- Web scraping with support for scraping, crawling, screenshots, and structured data extraction
12- Document conversion tools for text extraction, PDF operations, video processing
13- Extract data from documents, images, audio, and video
14- AI capabilities including agent completions, knowledge base management, and image generation
15- Developer tools for running JavaScript and Python code in a secure environment
16- Automatic error handling and detailed response formatting
17 
18## Installation
19 
20### Installing via Smithery
21 
22To install mcp-server-dumplingai for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Dumpling-AI/mcp-server-dumplingai):
23 
24```bash
25npx -y @smithery/cli install @Dumpling-AI/mcp-server-dumplingai --client claude
26```
27 
28### Running with npx
29 
30```bash
31env DUMPLING_API_KEY=your_api_key npx -y mcp-server-dumplingai
32```
33 
34### Manual Installation
35 
36```bash
37npm install -g mcp-server-dumplingai
38```
39 
40### Running on Cursor
41 
42Configuring Cursor 🖥️ Note: Requires Cursor version 0.45.6+
43 
44To configure Dumpling AI MCP in Cursor:
45 
461. Open Cursor Settings
472. Go to Features > MCP Servers
483. Click "+ Add New MCP Server"
494. Enter the following:
50 
51```
52{
53  "mcpServers": {
54    "dumplingai": {
55      "command": "npx",
56      "args": ["-y", "mcp-server-dumplingai"],
57      "env": {
58        "DUMPLING_API_KEY": "<your-api-key>"
59      }
60    }
61  }
62}
63```
64 
65> If you are using Windows and are running into issues, try `cmd /c "set DUMPLING_API_KEY=your-api-key && npx -y mcp-server-dumplingai"`
66 
67Replace `your-api-key` with your Dumpling AI API key.
68 
69## Configuration
70 
71### Environment Variables
72 
73- `DUMPLING_API_KEY`: Your Dumpling AI API key (required)
74 
75## Available Tools
76 
77### Data APIs
78 
79#### 1. Get YouTube Transcript (`get-youtube-transcript`)
80 
81Extract transcripts from YouTube videos with optional timestamps.
82 
83```json
84{
85  "name": "get-youtube-transcript",
86  "arguments": {
87    "videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
88    "includeTimestamps": true,
89    "timestampsToCombine": 3,
90    "preferredLanguage": "en"
91  }
92}
93```
94 
95#### 2. Search (`search`)
96 
97Perform Google web searches and optionally scrape content from results.
98 
99```json
100{
101  "name": "search",
102  "arguments": {
103    "query": "machine learning basics",
104    "country": "us",
105    "language": "en",
106    "dateRange": "pastMonth",
107    "scrapeResults": true,
108    "numResultsToScrape": 3,
109    "scrapeOptions": {
110      "format": "markdown",
111      "cleaned": true
112    }
113  }
114}
115```
116 
117#### 3. Get Autocomplete (`get-autocomplete`)
118 
119Get Google search autocomplete suggestions for a query.
120 
121```json
122{
123  "name": "get-autocomplete",
124  "arguments": {
125    "query": "how to learn",
126    "country": "us",
127    "language": "en",
128    "location": "New York"
129  }
130}
131```
132 
133#### 4. Search Maps (`search-maps`)
134 
135Search Google Maps for locations and businesses.
136 
137```json
138{
139  "name": "search-maps",
140  "arguments": {
141    "query": "coffee shops",
142    "gpsPositionZoom": "37.7749,-122.4194,14z",
143    "language": "en",
144    "page": 1
145  }
146}
147```
148 
149#### 5. Search Places (`search-places`)
150 
151Search for places with more detailed information.
152 
153```json
154{
155  "name": "search-places",
156  "arguments": {
157    "query": "hotels in paris",
158    "country": "fr",
159    "language": "en",
160    "page": 1
161  }
162}
163```
164 
165#### 6. Search News (`search-news`)
166 
167Search for news articles with customizable parameters.
168 
169```json
170{
171  "name": "search-news",
172  "arguments": {
173    "query": "climate change",
174    "country": "us",
175    "language": "en",
176    "dateRange": "pastWeek"
177  }
178}
179```
180 
181#### 7. Get Google Reviews (`get-google-reviews`)
182 
183Retrieve Google reviews for businesses or places.
184 
185```json
186{
187  "name": "get-google-reviews",
188  "arguments": {
189    "businessName": "Eiffel Tower",
190    "location": "Paris, France",
191    "limit": 10,
192    "sortBy": "relevance"
193  }
194}
195```
196 
197### Web Scraping
198 
199#### 8. Scrape (`scrape`)
200 
201Extract content from a web page with formatting options.
202 
203```json
204{
205  "name": "scrape",
206  "arguments": {
207    "url": "https://example.com",
208    "format": "markdown",
209    "cleaned": true,
210    "renderJs": true
211  }
212}
213```
214 
215#### 9. Crawl (`crawl`)
216 
217Recursively crawl websites and extract content with customizable parameters.
218 
219```json
220{
221  "name": "crawl",
222  "arguments": {
223    "baseUrl": "https://example.com",
224    "maxPages": 10,
225    "crawlBeyondBaseUrl": false,
226    "depth": 2,
227    "scrapeOptions": {
228      "format": "markdown",
229      "cleaned": true,
230      "renderJs": true
231    }
232  }
233}
234```
235 
236#### 10. Screenshot (`screenshot`)
237 
238Capture screenshots of web pages with customizable viewport and format options.
239 
240```json
241{
242  "name": "screenshot",
243  "arguments": {
244    "url": "https://example.com",
245    "width": 1280,
246    "height": 800,
247    "fullPage": true,
248    "format": "png",
249    "waitFor": 1000
250  }
251}
252```
253 
254#### 11. Extract (`extract`)
255 
256Extract structured data from web pages using AI-powered instructions.
257 
258```json
259{
260  "name": "extract",
261  "arguments": {
262    "url": "https://example.com/products",
263    "instructions": "Extract all product names, prices, and descriptions from this page",
264    "schema": {
265      "products": [
266        {
267          "name": "string",
268          "price": "number",
269          "description": "string"
270        }
271      ]
272    },
273    "renderJs": true
274  }
275}
276```
277 
278### Document Conversion
279 
280#### 12. Doc to Text (`doc-to-text`)
281 
282Convert documents to plaintext with optional OCR.
283 
284```json
285{
286  "name": "doc-to-text",
287  "arguments": {
288    "url": "https://example.com/document.pdf",
289    "options": {
290      "ocr": true,
291      "language": "en"
292    }
293  }
294}
295```
296 
297#### 13. Convert to PDF (`convert-to-pdf`)
298 
299Convert various file formats to PDF.
300 
301```json
302{
303  "name": "convert-to-pdf",
304  "arguments": {
305    "url": "https://example.com/document.docx",
306    "format": "docx",
307    "options": {
308      "quality": 90,
309      "pageSize": "A4",
310      "margin": 10
311    }
312  }
313}
314```
315 
316#### 14. Merge PDFs (`merge-pdfs`)
317 
318Combine multiple PDFs into a single document.
319 
320```json
321{
322  "name": "merge-pdfs",
323  "arguments": {
324    "urls": ["https://example.com/doc1.pdf", "https://example.com/doc2.pdf"],
325    "options": {
326      "addPageNumbers": true,
327      "addTableOfContents": true
328    }
329  }
330}
331```
332 
333#### 15. Trim Video (`trim-video`)
334 
335Extract a specific clip from a video.
336 
337```json
338{
339  "name": "trim-video",
340  "arguments": {
341    "url": "https://example.com/video.mp4",
342    "startTime": 30,
343    "endTime": 60,
344    "output": "mp4",
345    "options": {
346      "quality": 720,
347      "fps": 30
348    }
349  }
350}
351```
352 
353#### 16. Extract Document (`extract-document`)
354 
355Extract specific content from documents in various formats.
356 
357```json
358{
359  "name": "extract-document",
360  "arguments": {
361    "url": "https://example.com/document.pdf",
362    "format": "structured",
363    "options": {
364      "ocr": true,
365      "language": "en",
366      "includeMetadata": true
367    }
368  }
369}
370```
371 
372#### 17. Extract Image (`extract-image`)
373 
374Extract text and information from images.
375 
376```json
377{
378  "name": "extract-image",
379  "arguments": {
380    "url": "https://example.com/image.jpg",
381    "extractionType": "text",
382    "options": {
383      "language": "en",
384      "detectOrientation": true
385    }
386  }
387}
388```
389 
390#### 18. Extract Audio (`extract-audio`)
391 
392Transcribe and extract information from audio files.
393 
394```json
395{
396  "name": "extract-audio",
397  "arguments": {
398    "url": "https://example.com/audio.mp3",
399    "language": "en",
400    "options": {
401      "model": "enhanced",
402      "speakerDiarization": true,
403      "wordTimestamps": true
404    }
405  }
406}
407```
408 
409#### 19. Extract Video (`extract-video`)
410 
411Extract content from videos including transcripts, scenes, and objects.
412 
413```json
414{
415  "name": "extract-video",
416  "arguments": {
417    "url": "https://example.com/video.mp4",
418    "extractionType": "transcript",
419    "options": {
420      "language": "en",
421      "speakerDiarization": true
422    }
423  }
424}
425```
426 
427#### 20. Read PDF Metadata (`read-pdf-metadata`)
428 
429Extract metadata from PDF files.
430 
431```json
432{
433  "name": "read-pdf-metadata",
434  "arguments": {
435    "url": "https://example.com/document.pdf",
436    "includeExtended": true
437  }
438}
439```
440 
441#### 21. Write PDF Metadata (`write-pdf-metadata`)
442 
443Update metadata in PDF files.
444 
445```json
446{
447  "name": "write-pdf-metadata",
448  "arguments": {
449    "url": "https://example.com/document.pdf",
450    "metadata": {
451      "title": "New Title",
452      "author": "John Doe",
453      "keywords": ["keyword1", "keyword2"]
454    }
455  }
456}
457```
458 
459### AI
460 
461#### 22. Generate Agent Completion (`generate-agent-completion`)
462 
463Get AI agent completions with optional tool definitions.
464 
465```json
466{
467  "name": "generate-agent-completion",
468  "arguments": {
469    "prompt": "How can I improve my website's SEO?",
470    "model": "gpt-4",
471    "temperature": 0.7,
472    "maxTokens": 500,
473    "context": ["The website is an e-commerce store selling handmade crafts."]
474  }
475}
476```
477 
478#### 23. Search Knowledge Base (`search-knowledge-base`)
479 
480Search a knowledge base for relevant information.
481 
482```json
483{
484  "name": "search-knowledge-base",
485  "arguments": {
486    "kbId": "kb_12345",
487    "query": "How to optimize database performance",
488    "limit": 5,
489    "similarityThreshold": 0.7
490  }
491}
492```
493 
494#### 24. Add to Knowledge Base (`add-to-knowledge-base`)
495 
496Add entries to a knowledge base.
497 
498```json
499{
500  "name": "add-to-knowledge-base",
501  "arguments": {
502    "kbId": "kb_12345",
503    "entries": [
504      {
505        "text": "MongoDB is a document-based NoSQL database.",
506        "metadata": {
507          "source": "MongoDB documentation",
508          "category": "databases"
509        }
510      }
511    ],
512    "upsert": true
513  }
514}
515```
516 
517#### 25. Generate AI Image (`generate-ai-image`)
518 
519Generate images using AI models.
520 
521```json
522{
523  "name": "generate-ai-image",
524  "arguments": {
525    "prompt": "A futuristic city with flying cars and neon lights",
526    "width": 1024,
527    "height": 1024,
528    "numImages": 1,
529    "quality": "hd",
530    "style": "photorealistic"
531  }
532}
533```
534 
535#### 26. Generate Image (`generate-image`)
536 
537Generate images using various AI providers.
538 
539```json
540{
541  "name": "generate-image",
542  "arguments": {
543    "prompt": "A golden retriever in a meadow of wildflowers",
544    "provider": "dalle",
545    "width": 1024,
546    "height": 1024,
547    "numImages": 1
548  }
549}
550```
551 
552### Developer Tools
553 
554#### 27. Run JavaScript Code (`run-js-code`)
555 
556Execute JavaScript code with optional dependencies.
557 
558```json
559{
560  "name": "run-js-code",
561  "arguments": {
562    "code": "const result = [1, 2, 3, 4].reduce((sum, num) => sum + num, 0); console.log(`Sum: ${result}`); return result;",
563    "dependencies": {
564      "lodash": "^4.17.21"
565    },
566    "timeout": 5000
567  }
568}
569```
570 
571#### 28. Run Python Code (`run-python-code`)
572 
573Execute Python code with optional dependencies.
574 
575```json
576{
577  "name": "run-python-code",
578  "arguments": {
579    "code": "import numpy as np\narr = np.array([1, 2, 3, 4, 5])\nmean = np.mean(arr)\nprint(f'Mean: {mean}')\nreturn mean",
580    "dependencies": ["numpy", "pandas"],
581    "timeout": 10000,
582    "saveOutputFiles": true
583  }
584}
585```
586 
587## Error Handling
588 
589The server provides robust error handling:
590 
591- Detailed error messages with HTTP status codes
592- API key validation
593- Input validation using Zod schemas
594- Network error handling with descriptive messages
595 
596Example error response:
597 
598```json
599{
600  "content": [
601    {
602      "type": "text",
603      "text": "Error: Failed to fetch YouTube transcript: 404 Not Found"
604    }
605  ],
606  "isError": true
607}
608```
609 
610## Development
611 
612```bash
613# Install dependencies
614npm install
615 
616# Build
617npm run build
618 
619```
620 
621## License
622 
623MIT License - see LICENSE file for details
624