Connects Claude and other MCP agents to compress.new's markdown conversion API through a single fetch_url tool. Pass any URL and get back clean, token-optimized markdown with all the query parameters the service supports: compress for token reduction via substring replacement, main_only to strip navigation and boilerplate, selector for CSS-based extraction, and flags for metadata, schema.org data, or image retention. The response includes token counts in custom headers so you know exactly what you're feeding into context. Setup is just pointing your agent at https://mcp.compress.new in your MCP config. Useful when you need agents to autonomously pull web content without dumping raw HTML into prompts or when you're building research workflows that hit multiple sources in one session.
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