mcp -dumplingai
MCP (Model Context Protocol) server for Dumpling AI
claude mcp add --transport stdio dumplingai-mcp-server-dumplingai npx -y mcp-server-dumplingai \ --env DUMPLING_API_KEY="<your-api-key>"
How to use
The Dumpling AI MCP Server integrates Dumpling AI capabilities into the Model Context Protocol ecosystem. It exposes a wide range of data APIs, web scraping and crawling tools, document and media conversion, and AI-assisted capabilities such as agent completions and knowledge base management. The server also provides developer tooling to run JavaScript and Python code in a secure environment, enabling you to execute custom logic as part of your MCP workflows. To use it, configure an MCP client (e.g., Cursor or your own MCP client) to connect to the dumplingai MCP server using the provided mcpServers.dumplingai settings, including your Dumpling AI API key. Once connected, you can invoke the listed tools by name (e.g., get-youtube-transcript, search, scrape, extract, doc-to-text, etc.) and pass the required arguments as shown in the README examples.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- Access to a Dumpling AI API key
Installation steps:
- Install the MCP server globally via npm:
npm install -g mcp-server-dumplingai
- Run the MCP server with npx (as shown in the README):
env DUMPLING_API_KEY=your_api_key npx -y mcp-server-dumplingai
- (Optional) Use Smithery for automatic installation in Desktop environments:
npx -y @smithery/cli install @Dumpling-AI/mcp-server-dumplingai --client claude
- If you want to configure Cursor, add the MCP server configuration in Cursor's MCP Servers feature using the JSON snippet provided in the README. Replace the placeholder with your actual API key.
Additional notes
Notes and tips:
- Environment variable DUMPLING_API_KEY is required for authentication with the Dumpling AI API.
- When using Cursor on Windows, you may need to wrap the command as: cmd /c "set DUMPLING_API_KEY=your-api-key && npx -y mcp-server-dumplingai".
- The server exposes a rich set of tools (data APIs like get-youtube-transcript, search, search-places, etc.; web scraping with scrape/crawl/screenshot; document conversion with doc-to-text/convert-to-pdf/merge-pdfs; and AI features for agents and knowledge bases). Consult the README for the exact argument schemas.
- Always keep your API key secure and do not expose it in client-side code or publicly accessible configurations.
- If you update the package or CLI, ensure the mcpServers configuration remains compatible with any changes in tool names or argument formats.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.