MCP Catalogs
Home

aws-security-mcp

by groovyBugify·83·Score 43

A MCP server connecting AI assistants to AWS security services for infrastructure analysis.

securityops-infraai-llm
15
Forks
1
Open issues
10 mo ago
Last commit
2d ago
Indexed

Overview

AWS Security MCP enables AI assistants like Claude to perform comprehensive security analysis of AWS infrastructure through natural language queries. It bridges the gap between AI capabilities and AWS security services, allowing automatic discovery and analysis of resources across multiple AWS accounts. The system integrates findings from GuardDuty, SecurityHub, and Access Analyzer while providing infrastructure mapping and Athena-powered log analytics capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Security analysts can query AWS resources using natural language to identify misconfigurations
you:DevOps teams can monitor blast radius of specific resources across AWS organization
you:Compliance officers can check security status across multiple AWS accounts
you:What AWS permissions are required?
you:Can it work with non-Claude MCP clients?

When to choose this

Choose this MCP server if you need AI-powered security analysis of AWS infrastructure through natural language queries and are already using AWS security services like GuardDuty and SecurityHub.

When NOT to choose this

Don't choose this if you need security analysis for non-AWS cloud providers, write access to resources (this is read-only), or if you're on a free tier of Claude (requires Pro/Max for larger token limits).

Tools this server exposes

12 tools extracted from the README
  • query_aws_resources

    Query AWS resources across multiple services including EC2, S3, IAM, Lambda, and GuardDuty

  • analyze_security_findings

    Analyze security findings from GuardDuty and SecurityHub

  • cross_account_analysis

    Perform security analysis across multiple AWS accounts

  • blast_radius_analysis

    Generate blast radius analysis for AWS resources

  • athena_log_analysis

    Analyze AWS logs using Athena including CloudTrail and VPC Flow Logs

  • network_topology_analysis

    Analyze network topology including VPCs, security groups, and load balancers

  • refresh_aws_session

    Refresh AWS session credentials for cross-account access

  • security_compliance_check

    Check security compliance against AWS standards and frameworks

  • analyze_lambda_security

    Analyze Lambda functions for security vulnerabilities

  • s3_security_analysis

    Analyze S3 buckets for security misconfigurations

  • access_analyzer_check

    Use IAM Access Analyzer to check for potentially unauthorized access

  • generate_security_report

    Generate comprehensive security reports across AWS infrastructure

Note: Tools were inferred from usage examples and service descriptions rather than a dedicated tools section. The README doesn't provide explicit tool names or parameters, but rather shows how users can interact with the system through natural la

Comparable tools

aws-mcpsecurity-hub-mcpguardduty-mcp

Installation

Local Setup

  1. Clone and set up the repository:

``bash git clone https://github.com/groovyBugify/aws-security-mcp.git cd aws-security-mcp uv venv source .venv/bin/activate uv pip install -r requirements.txt ``

  1. Configure your AWS credentials via SSO or environment variables
  2. Configure Claude Desktop:

``json { "mcpServers": { "aws-security": { "command": "/path/to/mcp-proxy", "args": ["http://localhost:8000/sse"] } } }``

FAQ

What AWS permissions are required?
The server needs the SecurityAudit policy and STS AssumeRole permissions for cross-account access. Athena permissions are optional for log analysis features.
Can it work with non-Claude MCP clients?
Yes, it should work with any MCP client that supports SSE connections, like Cline. The mcp-proxy component helps bridge the connection.

Compare aws-security-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.