MCP Observatory
1m ago Tracked 55,290 Last 1m ago 24h 3,023

Capability drift in headroomlabs-ai/headroom

github headroomlabs-ai/headroom D

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

maintainer
headroomlabs-ai
tools
0
CVEs
0
releases
115
advisory #775459
HIGH headroomlabs-ai/headroom

code analysis flagged committed secret ×2 in headroomlabs-ai/headroom

current permission surface (inferred):

drift timeline for headroomlabs-ai/headroom → security tab →

drift history for this server newest 8
  1. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  2. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  3. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  4. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  5. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  6. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  7. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom
  8. HIGH code analysis flagged committed secret ×2 in headroomlabs-ai/headroom

Each entry is one capability capture differing from the one before it — a review signal, not a verdict.