dumpling ai mcp server

a model context protocol (mcp) server implementation that integrates with dumpling ai for data scraping, content processing, knowledge management, ai agents, and code execution capabilities.

features

• complete integration with all dumpling ai api endpoints
• data apis for youtube transcripts, search, autocomplete, maps, places, news, and reviews
• web scraping with support for scraping, crawling, screenshots, and structured data extraction
• document conversion tools for text extraction, pdf operations, video processing
• extract data from documents, images, audio, and video
• ai capabilities including agent completions, knowledge base management, and image generation
• developer tools for running javascript and python code in a secure environment
• automatic error handling and detailed response formatting

installation

installing via smithery

to install mcp-server-dumplingai for claude desktop automatically via smithery:

npx -y @smithery/cli install @dumpling-ai/mcp-server-dumplingai --client claude

running with npx

env dumpling_api_key=your_api_key npx -y mcp-server-dumplingai

manual installation

npm install -g mcp-server-dumplingai

running on cursor

configuring cursor 🖥️ note: requires cursor version 0.45.6+

to configure dumpling ai mcp in cursor:

1. open cursor settings
2. go to features > mcp servers
3. click "+ add new mcp server"
4. enter the following:

{
  "mcpservers": {
    "dumplingai": {
      "command": "npx",
      "args": ["-y", "mcp-server-dumplingai"],
      "env": {
        "dumpling_api_key": "<your-api-key>"
      }
    }
  }
}

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"

replace your-api-key with your dumpling ai api key.

configuration

environment variables

• dumpling_api_key: your dumpling ai api key (required)

available tools

data apis

1. get youtube transcript (get-youtube-transcript)

extract transcripts from youtube videos with optional timestamps.

{
  "name": "get-youtube-transcript",
  "arguments": {
    "videourl": "https://www.youtube.com/watch?v=dqw4w9wgxcq",
    "includetimestamps": true,
    "timestampstocombine": 3,
    "preferredlanguage": "en"
  }
}

2. search (search)

perform google web searches and optionally scrape content from results.

{
  "name": "search",
  "arguments": {
    "query": "machine learning basics",
    "country": "us",
    "language": "en",
    "daterange": "pastmonth",
    "scraperesults": true,
    "numresultstoscrape": 3,
    "scrapeoptions": {
      "format": "markdown",
      "cleaned": true
    }
  }
}

3. get autocomplete (get-autocomplete)

get google search autocomplete suggestions for a query.

{
  "name": "get-autocomplete",
  "arguments": {
    "query": "how to learn",
    "country": "us",
    "language": "en",
    "location": "new york"
  }
}

4. search maps (search-maps)

search google maps for locations and businesses.

{
  "name": "search-maps",
  "arguments": {
    "query": "coffee shops",
    "gpspositionzoom": "37.7749,-122.4194,14z",
    "language": "en",
    "page": 1
  }
}

5. search places (search-places)

search for places with more detailed information.

{
  "name": "search-places",
  "arguments": {
    "query": "hotels in paris",
    "country": "fr",
    "language": "en",
    "page": 1
  }
}

6. search news (search-news)

search for news articles with customizable parameters.

{
  "name": "search-news",
  "arguments": {
    "query": "climate change",
    "country": "us",
    "language": "en",
    "daterange": "pastweek"
  }
}

7. get google reviews (get-google-reviews)

retrieve google reviews for businesses or places.

{
  "name": "get-google-reviews",
  "arguments": {
    "businessname": "eiffel tower",
    "location": "paris, france",
    "limit": 10,
    "sortby": "relevance"
  }
}

web scraping

8. scrape (scrape)

extract content from a web page with formatting options.

{
  "name": "scrape",
  "arguments": {
    "url": "https://example.com",
    "format": "markdown",
    "cleaned": true,
    "renderjs": true
  }
}

9. crawl (crawl)

recursively crawl websites and extract content with customizable parameters.

{
  "name": "crawl",
  "arguments": {
    "baseurl": "https://example.com",
    "maxpages": 10,
    "crawlbeyondbaseurl": false,
    "depth": 2,
    "scrapeoptions": {
      "format": "markdown",
      "cleaned": true,
      "renderjs": true
    }
  }
}

10. screenshot (screenshot)

capture screenshots of web pages with customizable viewport and format options.

{
  "name": "screenshot",
  "arguments": {
    "url": "https://example.com",
    "width": 1280,
    "height": 800,
    "fullpage": true,
    "format": "png",
    "waitfor": 1000
  }
}

11. extract (extract)

extract structured data from web pages using ai-powered instructions.

{
  "name": "extract",
  "arguments": {
    "url": "https://example.com/products",
    "instructions": "extract all product names, prices, and descriptions from this page",
    "schema": {
      "products": [
        {
          "name": "string",
          "price": "number",
          "description": "string"
        }
      ]
    },
    "renderjs": true
  }
}

document conversion

12. doc to text (doc-to-text)

convert documents to plaintext with optional ocr.

{
  "name": "doc-to-text",
  "arguments": {
    "url": "https://example.com/document.pdf",
    "options": {
      "ocr": true,
      "language": "en"
    }
  }
}

13. convert to pdf (convert-to-pdf)

convert various file formats to pdf.

{
  "name": "convert-to-pdf",
  "arguments": {
    "url": "https://example.com/document.docx",
    "format": "docx",
    "options": {
      "quality": 90,
      "pagesize": "a4",
      "margin": 10
    }
  }
}

14. merge pdfs (merge-pdfs)

combine multiple pdfs into a single document.

{
  "name": "merge-pdfs",
  "arguments": {
    "urls": ["https://example.com/doc1.pdf", "https://example.com/doc2.pdf"],
    "options": {
      "addpagenumbers": true,
      "addtableofcontents": true
    }
  }
}

15. trim video (trim-video)

extract a specific clip from a video.

{
  "name": "trim-video",
  "arguments": {
    "url": "https://example.com/video.mp4",
    "starttime": 30,
    "endtime": 60,
    "output": "mp4",
    "options": {
      "quality": 720,
      "fps": 30
    }
  }
}

16. extract document (extract-document)

extract specific content from documents in various formats.

{
  "name": "extract-document",
  "arguments": {
    "url": "https://example.com/document.pdf",
    "format": "structured",
    "options": {
      "ocr": true,
      "language": "en",
      "includemetadata": true
    }
  }
}

17. extract image (extract-image)

extract text and information from images.

{
  "name": "extract-image",
  "arguments": {
    "url": "https://example.com/image.jpg",
    "extractiontype": "text",
    "options": {
      "language": "en",
      "detectorientation": true
    }
  }
}

18. extract audio (extract-audio)

transcribe and extract information from audio files.

{
  "name": "extract-audio",
  "arguments": {
    "url": "https://example.com/audio.mp3",
    "language": "en",
    "options": {
      "model": "enhanced",
      "speakerdiarization": true,
      "wordtimestamps": true
    }
  }
}

19. extract video (extract-video)

extract content from videos including transcripts, scenes, and objects.

{
  "name": "extract-video",
  "arguments": {
    "url": "https://example.com/video.mp4",
    "extractiontype": "transcript",
    "options": {
      "language": "en",
      "speakerdiarization": true
    }
  }
}

20. read pdf metadata (read-pdf-metadata)

extract metadata from pdf files.

{
  "name": "read-pdf-metadata",
  "arguments": {
    "url": "https://example.com/document.pdf",
    "includeextended": true
  }
}

21. write pdf metadata (write-pdf-metadata)

update metadata in pdf files.

{
  "name": "write-pdf-metadata",
  "arguments": {
    "url": "https://example.com/document.pdf",
    "metadata": {
      "title": "new title",
      "author": "john doe",
      "keywords": ["keyword1", "keyword2"]
    }
  }
}

ai

22. generate agent completion (generate-agent-completion)

get ai agent completions with optional tool definitions.

{
  "name": "generate-agent-completion",
  "arguments": {
    "prompt": "how can i improve my website's seo?",
    "model": "gpt-4",
    "temperature": 0.7,
    "maxtokens": 500,
    "context": ["the website is an e-commerce store selling handmade crafts."]
  }
}

23. search knowledge base (search-knowledge-base)

search a knowledge base for relevant information.

{
  "name": "search-knowledge-base",
  "arguments": {
    "kbid": "kb_12345",
    "query": "how to optimize database performance",
    "limit": 5,
    "similaritythreshold": 0.7
  }
}

24. add to knowledge base (add-to-knowledge-base)

add entries to a knowledge base.

{
  "name": "add-to-knowledge-base",
  "arguments": {
    "kbid": "kb_12345",
    "entries": [
      {
        "text": "mongodb is a document-based nosql database.",
        "metadata": {
          "source": "mongodb documentation",
          "category": "databases"
        }
      }
    ],
    "upsert": true
  }
}

25. generate ai image (generate-ai-image)

generate images using ai models.

{
  "name": "generate-ai-image",
  "arguments": {
    "prompt": "a futuristic city with flying cars and neon lights",
    "width": 1024,
    "height": 1024,
    "numimages": 1,
    "quality": "hd",
    "style": "photorealistic"
  }
}

26. generate image (generate-image)

generate images using various ai providers.

{
  "name": "generate-image",
  "arguments": {
    "prompt": "a golden retriever in a meadow of wildflowers",
    "provider": "dalle",
    "width": 1024,
    "height": 1024,
    "numimages": 1
  }
}

developer tools

27. run javascript code (run-js-code)

execute javascript code with optional dependencies.

{
  "name": "run-js-code",
  "arguments": {
    "code": "const result = [1, 2, 3, 4].reduce((sum, num) => sum + num, 0); console.log(`sum: ${result}`); return result;",
    "dependencies": {
      "lodash": "^4.17.21"
    },
    "timeout": 5000
  }
}

28. run python code (run-python-code)

execute python code with optional dependencies.

{
  "name": "run-python-code",
  "arguments": {
    "code": "import numpy as np\narr = np.array([1, 2, 3, 4, 5])\nmean = np.mean(arr)\nprint(f'mean: {mean}')\nreturn mean",
    "dependencies": ["numpy", "pandas"],
    "timeout": 10000,
    "saveoutputfiles": true
  }
}

error handling

the server provides robust error handling:

• detailed error messages with http status codes
• api key validation
• input validation using zod schemas
• network error handling with descriptive messages

example error response:

{
  "content": [
    {
      "type": "text",
      "text": "error: failed to fetch youtube transcript: 404 not found"
    }
  ],
  "iserror": true
}

development

# install dependencies
npm install

# build
npm run build

license

mit license - see license file for details