Cline MCP Server
Enables web search using DuckDuckGo's HTML results page without an API key.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cline MCP Serversearch for latest React 19 features"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cline MCP Server
An MCP (Model Context Protocol) server that adds web search, image search, image downloading, webpage reading, command execution, and PDF parsing — all without needing API keys.
Tools
Tool | Description |
| Search the web via DuckDuckGo (no API key needed) |
| Search for images with pagination and pixel size filtering |
| Fetch and extract readable text from any URL |
| Download images from URLs to local files (absolute path required) |
| Run shell commands with safety checks |
| Extract text from local or remote PDF files |
Related MCP server: mcp-web-calc
Setup
1. Build the server
npm install
npm run build2. Configure as MCP server
Add this entry to your MCP settings (adjust the path to where you cloned this repo):
{
"mcpServers": {
"cline-tools": {
"command": "node",
"args": ["<path-to-repo>/dist/index.js"],
"disabled": false
}
}
}3. Restart your IDE/client
After saving the config, restart the extension or reload the window. The tools should appear in the MCP tools list.
Usage Examples
Search the web:
"Search for the latest React 19 features"
Search for images (with pagination):
"Find images of Pirelli tyres, page 2, minimum 1920px wide"
Read a webpage:
"Fetch the content from https://docs.python.org/3/tutorial/"
Download images:
"Download the image at https://example.com/photo.jpg to /Users/you/project/downloads/photo.jpg"
Run commands:
"Run
ls -lain my home directory"
Read PDFs:
"Extract the text from /Users/you/documents/paper.pdf"
Development
# Run in development mode (no build needed)
npm run dev
# Build for production
npm run build
# Run the built server
npm startHow It Works
Web search scrapes DuckDuckGo's HTML results page (no API key required)
Image search uses DuckDuckGo's image API with pagination and client-side pixel filtering
Webpage fetching uses Cheerio to extract clean text, stripping ads/nav/scripts
Image download streams the file to disk with content-type validation (requires absolute paths)
Command execution has a blocklist for dangerous patterns (rm -rf /, fork bombs, etc.)
PDF reading works with both local files and URLs
Requirements
Node.js 20+
No API keys needed — everything works out of the box
This server cannot be deployed
Maintenance
Related MCP Connectors
PDF, image, video, OCR, screenshot, SQL, QR and text tools for agents. No API key, no signup.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides filesystem, web search, SQLite, and system tools for AI assistants like Claude, enabling secure access to local resources and the web.6MIT
- AlicenseNot gradedqualityCmaintenanceProvides web search, URL fetching, summarization, math evaluation, and Wikipedia tools for LM Studio without needing an API key.3MIT
- AlicenseAqualityBmaintenanceProvides local agent capabilities for LM Studio including file I/O, terminal execution, and web search.1180 PyPIMIT
- AlicenseAqualityCmaintenanceEnables web search, scraping, and live package version lookup for local LLMs, with no API keys required.52MIT