What are the runtime requirements?
Node.js and npm are required. The server is built and run using Node.js.
@treaties-ai
Basic information
MCP server for scanning local code and localhost URLs
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"local-scanner-mcp": {
"url": "http://localhost:3000",
"waitTime": 2000,
"actions": [
{
"type": "click",
"selector": "#login-button"
},
{
"type": "type",
"selector": "#username",
"text": "testuser"
},
{
"type": "type",
"selector": "#password",
"text": "password"
},
{
"type": "click",
"selector": "#submit-button"
},
{
"type": "wait",
"time": 1000
}
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list directly from this server's endpoint using the button above.
Local Scanner MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to scan local code and localhost URLs. It provides tools for validating code style, capturing screenshots of local web pages, analyzing console logs, and checking HTML compliance. It is designed for developers using AI assistants like Cline (VSCode) or Cascade (WindSurf) to interact with local development environments.
Install dependencies with npm install, build with npm run build, and start with npm start. Then configure an MCP client (e.g., for Cline or WindSurf) by editing the respective settings file and providing the path to the built server (build/index.js). The server exposes four tools: scan_localhost, screenshot_localhost, lint_code, and validate_html.
Node.js and npm are required. The server is built and run using Node.js.
Edit the MCP settings file: for Cline, `~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json`; for WindSurf, `~/Library/Application Support/WindSurf/windsurf_config.json`. Add an entry with command "node" and args pointing to `build/index.js`.
Only URLs starting with `http://localhost` or `https://localhost` are allowed.
JavaScript, TypeScript, and CSS files. Language can be auto-detected from file extension or specified manually.
Yes, `scan_localhost` accepts an optional `actions` list for clicking, typing, and waiting.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Painless E2E Automation for Mobile and Web
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Open-source MCP to use Blender with any LLM
Comments