Dumpling AI

You can run and connect to the Dumpling AI MCP Server locally to access data APIs, web scraping, document conversion, AI capabilities, and developer tools. This MCP server lets you interact with Dumpling AI services from your client, manage knowledge, execute code securely, and automate data extraction workflows.

How to use

To use the Dumpling AI MCP Server, start it as a local process or run it through a package runner and connect your MCP client to it. You will provide your API key to authorize requests, then invoke the available MCP endpoints through your client to fetch transcripts, run scrapes, extract structured data, generate AI content, or execute code in a sandboxed environment. The server handles errors gracefully and returns structured responses that your client can parse and display.

How to install

Prerequisites: you need Node.js and npm installed on your machine. Node.js provides the runtime and npm handles package installation.

Install the MCP server globally using npm to access the command line interface.

npm install -g mcp-server-dumplingai

Run the MCP server locally with npx, supplying your API key in the environment.

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

If you prefer automatic installation via a package manager helper, you can install via Smithery and then run the server with the same environment variable.

npx -y @smithery/cli install @Dumpling-AI/mcp-server-dumplingai --client claude

To configure the server in Cursor, you can add a new MCP Server entry with the following configuration. Replace your-api-key with your actual Dumpling AI API key.

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

Configuration

Environment variables: the server requires DUMPLING_API_KEY to authorize requests. Include this in your environment when starting the server.

Security and troubleshooting

The MCP server provides robust error handling and detailed response formatting. If you encounter errors, verify your API key is correct and that the server process is running. Common issues include network connectivity problems or invalid inputs, which will produce descriptive error messages with status codes to guide debugging.

Notes and examples

The server supports numerous data APIs and tools for data extraction, AI agent interactions, and code execution within a secure environment. Use your MCP client to call the available endpoints and handle responses in your application logic.

Available tools

get-youtube-transcript

Extract transcripts from YouTube videos with optional timestamps.

search

Perform Google web searches and optionally scrape content from results.

get-autocomplete

Get Google search autocomplete suggestions for a query.

search-maps

Search Google Maps for locations and businesses.

search-places

Search for places with more detailed information.

search-news

Search for news articles with customizable parameters.

get-google-reviews

Retrieve Google reviews for businesses or places.

scrape

Extract content from a web page with formatting options.

crawl

Recursively crawl websites and extract content with customizable parameters.

screenshot

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

extract

Extract structured data from web pages using AI-powered instructions.

doc-to-text

Convert documents to plaintext with optional OCR.

convert-to-pdf

Convert various file formats to PDF.

merge-pdfs

Combine multiple PDFs into a single document.

trim-video

Extract a specific clip from a video.

extract-document

Extract content from documents in various formats.

extract-image

Extract text and information from images.

extract-audio

Transcribe and extract information from audio files.

extract-video

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

read-pdf-metadata

Extract metadata from PDF files.

write-pdf-metadata

Update metadata in PDF files.

generate-agent-completion

Get AI agent completions with optional tool definitions.

search-knowledge-base

Search a knowledge base for relevant information.

add-to-knowledge-base

Add entries to a knowledge base.

generate-ai-image

Generate images using AI models.

generate-image

Generate images using various AI providers.

run-js-code

Execute JavaScript code with optional dependencies.

run-python-code

Execute Python code with optional dependencies.