mcp-sentinel

mcp-sentinel is an Agent security & guardrails skill for AI agents, published by soy-rafa in the claude-mcp-sentinel repository on GitHub. Skillspace rates mcp-sentinel F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.

Security monitoring agent for Claude Skills and MCP servers. Real-time protection layer (PreToolUse hook, zero LLM cost by default): hard-blocks confirmed-malicious tool calls (known-bad domains from real incidents and an auto-updating URLhaus malware feed) and, for merely suspicious ones (credential exfiltration, reverse shells, curl|bash pipes, raw-IP URLs, cloud-metadata/IMDS, config/persistence writes), asks you to approve or deny at the native prompt instead of blocking outright. Approving a flagged path/domain is remembered so it stops asking (trust builds as you confirm what you use). v3 adds: multi-step attack-chain detection (credential access then egress), cross-server data-flow tracking, a config/MCP scanner + integrity baseline (catches a malicious hook planted in a cloned repo), a shadow/audit-only mode (SENTINEL_SHADOW: never blocks, just tallies what it would have stopped), and an OPTIONAL, off-by-default AI escalation layer (SENTINEL_AI: only for ambiguous cases,…

Grade
F
Quality
15 / 100
Safety
Unsafe
GitHub stars
185

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since.

View source on GitHubsoy-rafa/claude-mcp-sentinel

Our review

Architecture
68 / 100
Maturity
Structured: ships references or scripts
Security scan
Critical-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • pipe remote script to shell
  • reverse shell
  • exfiltration language
  • references sensitive credential env
  • accesses sensitive system files
  • dynamic code execution (eval/exec)
  • suspicious outbound endpoint
  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Agent security & guardrails

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.