bedrock-security-mcp

AUAggy/bedrock-security-mcp

★ 0 stars TypeScript AI/LLM Updated 9d ago

MCP server + CI-grade CLI that audits AWS Bedrock security posture: IAM, invocation logging, guardrails, prompt-injection signals. Maps to OWASP LLM Top 10, NIST AI RMF, MITRE ATLAS.

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": {
    "bedrock-security-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "AUAggy/bedrock-security-mcp"
      ]
    }
  }
}

README Excerpt

An MCP server with a CI-grade CLI. It audits the security posture of AWS Bedrock workloads: IAM roles with Bedrock permissions, model-invocation logging and its KMS encryption, guardrail quality, and prompt-injection signals in your invocation logs. Findings map to OWASP LLM Top 10 (2025), OWASP Agentic Applications Top 10, NIST AI RMF, and MITRE ATLAS.

Tools (4)

AWS_PROFILEAWS_REGIONBEDROCK_SECURITY_ACCOUNT_IDBEDROCK_SECURITY_OUTPUT_DIR

Topics

ai-securityawsbedrockmcpmodel-context-protocolprompt-injectionsecurity

bedrock-security-mcp

Quick Install

README Excerpt

Tools (4)

Topics

Related AI/LLM Servers