MCP-Sentinel

BashaarJavaid/MCP-Sentinel

★ 0 stars Python AI/LLM Updated today

Build-time security scanning for MCP servers — static + GPT-reviewed + Docker-verified findings mapped to the OWASP Agentic Top 10, with SARIF/GitHub Action support.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-sentinel": {
      "command": "uvx",
      "args": [
        "mcp-sentinel"
      ]
    }
  }
}

Or install with pip: pip install mcp-sentinel

README Excerpt

**Build-time security scanning for MCP servers.** AI agents invoke tools exposed by MCP servers, and a single unsafe tool can leak credentials, run arbitrary commands, or hijack the agent. MCP Sentinel catches those holes before you ship — it scans an MCP server and reports the security findings, each mapped to a known threat class.

Topics

agentic-aiai-securitydevsecopsdockergithub-actionsllm-securitymcpmodel-context-protocolowasppythonsarifsastsecurity-scannerstatic-analysissupply-chain-security

MCP-Sentinel

Quick Install

README Excerpt

Topics

Related AI/LLM Servers