Headless browser for AI agents — navigate, interact with, and test web pages via MCP.
Charlotte is an MCP server that gives AI agents full browser control through headless Chromium. It renders web pages into structured, agent-readable representations — extracting landmarks, interactive elements, forms, and content — so agents can understand and interact with any web page without parsing raw HTML. Charlotte provides 39 tools covering navigation, clicking, typing, screenshots, cookie management, network monitoring, visual diffing, accessibility auditing, and local development serving. Built for developers who want their AI agents to browse, test, and debug web applications.
Set these up before or after installing:
Environment variable: CHARLOTTE_CHROMIUM_PATH
Once installed, try these example prompts and explore these capabilities:
Add this to your MCP configuration file:
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@ticktockbent/charlotte"
],
"command": "npx"
}
}
}Valid MCP server (1 strong, 1 medium validity signals). 1 code issue detected. No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.
4 files analyzed · 2 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Be the first to review this server!
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by mcp-marketplace · Developer Tools
Scaffold, build, and publish TypeScript MCP servers to npm — conversationally
by mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by xt765 · Developer Tools
Convert PDF, DOCX, HTML, Markdown, and Text for AI assistant context injection.