Wraps compress.new's conversion API into a single MCP tool that turns any URL into clean, token-optimized markdown. Your agent calls fetch_url with a URL and optional parameters like compress, main_only, selector, or metadata, and gets back stripped content ready for reasoning. No more pasting raw HTML into prompts or burning context window on boilerplate. The service strips navigation, ads, and structural chrome automatically, and can compress repetitive strings into short tokens to save another 50-80%. Useful when your agent needs to read documentation, analyze articles, or pull live web content into its context without the overhead. Free to use, no API key required, works over HTTP transport.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent