TickTockBent/charlotte

Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps

48
/ 100
Emerging

This tool helps AI agents navigate and interact with web pages efficiently by providing structured, minimal information instead of overwhelming data dumps. It takes in raw web page content and outputs a concise, organized representation, allowing agents to understand and interact with pages without unnecessary processing. This is for developers building AI agents that need to browse and extract information from the web.

Available on npm.

Use this if you are building AI agents and want to significantly reduce the cost and improve the performance of their web browsing tasks by sending them only relevant, structured data.

Not ideal if your AI agent needs to process the raw, unstructured accessibility tree of a web page directly without any filtering or summarization.

AI Agent Development Web Scraping Automation Large Language Models Token Efficiency
Maintenance 10 / 25
Adoption 9 / 25
Maturity 20 / 25
Community 9 / 25

How are scores calculated?

Stars

97

Forks

6

Language

TypeScript

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/TickTockBent/charlotte"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.