Leaderboard/Compress.new
MCP ServerScored via MCP protocol probing: initialize handshake, tools/list conformance, and ping + tool invocation performance.

Compress.new

Convert any webpage to clean markdown and feed it directly into AI agent workflows. Why This Matters? Adding webpages to LLM conversations usually means dumping raw HTML, bloated with ads, scripts, and formatting noise. This MCP integrates compress.new into MCP-compatible AI agents to extract only the content you need: Lower token costs — Clean markdown vs. bloated HTML means fewer tokens per page Better context — Markdown is optimized for LLM comprehension; raw HTML introduces noise Precise extraction — Remove ads, sidebars, and cruft automatically One command — Just pass a URL; get ready-to-use content instantly Use it to research topics, analyze articles, gather documentation, or extract any webpage content without the overhead.

50/100
Operational Score
Score Breakdown
Availability30/30
Conformance10/30
Performance10/40
Key Metrics
Uptime 30d
100.0%
P95 Latency
626.5ms
Conformance
Fail
Trend
Stable
What's Being Tested
Availability
HTTP health check to the service endpoint
Responded with HTTP 404 in 528ms
Conformance
MCP initialize handshake + tools/list
MCP initialize handshake failed
Performance
MCP ping + zero-arg tool invocation benchmarking
P95 latency: 626ms, task completion: 0%
Improvement Tips
  • -Fix MCP initialize handshake errors
Recent Probe Results
TimestampStatusLatencyConformance
Apr 2, 2026success528.7msPartial
Apr 2, 2026success209.4msPartial
Apr 2, 2026success203.7msPartial
Apr 2, 2026success316.5msPartial
Apr 2, 2026success169.8msPartial
Apr 2, 2026success345.6msPartial
Apr 2, 2026success182.9msPartial
Apr 2, 2026success500.4msPartial
Apr 2, 2026success154.4msPartial
Apr 2, 2026success514.2msPartial
Source Registries
smithery
First Seen
Mar 26, 2026
Last Seen
Apr 1, 2026
Last Probed
Apr 2, 2026