cloud-audit
Connects Claude to the cloud-audit scanner, which walks AWS environments to find attack chains and IAM privilege escalation paths. You get tools to run full scans, generate blast radius graphs from a seed resource (EC2 instance, IAM role, Lambda, S3 bucket), detect active threat patterns from recent incidents, and simulate fixes before applying them. The blast radius command runs offline against saved scan data and outputs tree, Mermaid, or JSON formats you can drop into the live visualizer. Useful when you're triaging findings and need to answer "what can an attacker reach if this one resource is compromised" or "which fix collapses the most exposure." The threat feed checks for cryptomining, leaked credential scanners, and CVE patterns tied to 2025-2026 campaigns with research references attached.
- GitHub stars
- 59
- tools
- 7
- transport
- STDIO
- last updated
- Apr 17, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
scan_awsRun a full AWS security scan.
Run a full AWS security scan.
No parameter schema in public metadata yet.
get_findings
No parameter schema in public metadata yet.
get_attack_chains
No parameter schema in public metadata yet.
get_remediation
No parameter schema in public metadata yet.
get_health_score
No parameter schema in public metadata yet.
list_checks
No parameter schema in public metadata yet.
get_agent_blast
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
cloud-audit logo
cloud-audit
What can a hijacked AI agent reach in your AWS account, and can you prove it?
Open-source, read-only AWS security scanner. 110 checks, 64 IAM privilege-escalation methods, 31 attack-chain
rules, blast radius for any resource, and agent-blast for Bedrock Agents and AgentCore:
what a prompt-injected or credential-stolen agent can reach, with the IAM policy simulator as the witness.
Every finding ships an AWS CLI + Terraform fix. Nothing is written to your account.
Details
- Repository
- github.com/gebalamariusz/cloud-audit
- Website
- haitmg.pl/cloud-audit
- Categories
- Cloud & Infrastructure, Security & Pentesting
- Package
cloud-audit- Transport
- STDIO
- Registry
- MCP registry, active
Related Cloud & Infrastructure MCP servers
View all
Komodo MCP Servermp-tool/komodo-mcp-serverMCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI53stars
LibreNMS MCPmhajder/librenms-mcpMCP server for LibreNMS network monitoring - query devices, ports, alerts, and manage infrastructure42stars
devcontainer-mcpaniongithub/devcontainer-mcpManage dev container environments via MCP (Docker, DevPod, Codespaces).28stars
IONOS CLOUD MCP Serverionos-cloud/ionoscloud-mcpInspect and manage IONOS CLOUD infrastructure via MCP. Writes are opt-in and off by default.11stars
SearXNG HTTP MCPwhw23/searxng_http_mcpSelf-contained SearXNG metasearch MCP server. One Docker image, 200+ engines, privacy-first.8stars
Kubeviewmikhae1/kubeview-mcpRead-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.5stars