MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
- capability exposure inferred + 35
- tool safety inferred + 14
- supply-chain attested + 6
- trust mitigators mixed − 3
attested inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 4m ago · see ecosystem CVEs →
- D · 67 → C · 52
- D · 79 → D · 67
- D · 72 → D · 79
- C · 55 → D · 72
- D · 70 → C · 55
- C · 55 → D · 70
- C · 58 → C · 55
No known CVEs for this server.
- high dangerous code
dynamic exec: concat require() · obfuscated payload: dynamic require()/import()
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed v1.0.169 · analyzer v32 · 5h ago
skills & prompt files 21
- skill package/configs/antigravity-cli/skills/context-mode/SKILL.md
- agent-rules package/configs/antigravity/GEMINI.md
- agent-rules package/configs/claude-code/CLAUDE.md
- agent-rules package/configs/codex/AGENTS.md
- skill package/configs/copilot-cli/skills/context-mode/SKILL.md
- agent-rules package/configs/gemini-cli/GEMINI.md
- agent-rules package/configs/jetbrains-copilot/copilot-instructions.md
- agent-rules package/configs/kilo/AGENTS.md
- agent-rules package/configs/openclaw/AGENTS.md
- agent-rules package/configs/opencode/AGENTS.md
- agent-rules package/configs/pi/AGENTS.md
- agent-rules package/configs/vscode-copilot/copilot-instructions.md
- agent-rules package/configs/zed/AGENTS.md
- skill package/skills/context-mode/SKILL.md
- skill package/skills/ctx-doctor/SKILL.md
- skill package/skills/ctx-index/SKILL.md
- skill package/skills/ctx-insight/SKILL.md
- skill package/skills/ctx-purge/SKILL.md
- skill package/skills/ctx-search/SKILL.md
- skill package/skills/ctx-stats/SKILL.md
- skill package/skills/ctx-upgrade/SKILL.md
danger signals3
- dynamic code execution concat require() package/build/server.js :2557
const dns = require('no' + 'de:dns'); - dynamic code execution concat require() package/cli.bundle.mjs :668
const dns = require('no' + 'de:dns'); - dynamic code execution concat require() package/server.bundle.mjs :833
const dns = require('no' + 'de:dns');
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/npm:context-mode/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of mksglu.