cloud-audit — Claude Code MCP server: what it does, how to install
A read-only AWS scanner wired into your coding agent: attack-chain rules, IAM escalation routes and a blast-radius map per finding.
claude mcp add cloud-audit -- uvx cloud-auditWhat cloud-audit does
This MCP server gives the agent a scanner for AWS accounts. It carries 110 checks, 64 known ways to climb the IAM privilege ladder, and 31 rules for spotting attack chains. Nothing is written to the account you point it at. Setup goes through uvx cloud-audit and the same entry works in Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline and Zed.
agent-blast handles Bedrock Agents and AgentCore. For each agent it maps the roles sitting behind the tools, knowledge bases and gateways, then splits the result by threat model: the attacker holds a role's credentials, or they only got a prompt injected through a document or a ticket. Escalation paths are backed by the IAM policy simulator. Each finding arrives with an AWS CLI command and Terraform code that close it.
No account is needed to try it: cloud-audit demo --save demo.json builds a report from an invented account using the same engines. A real scan wants AWS credentials, and the AWS-managed SecurityAudit policy is enough for every check. The simulator reads identity policies, permissions boundaries and SCPs. Resource-based policies on the targets, RCPs and VPC endpoint policies fall outside it, so those edges of the report read friendlier than reality.
What it helps with
- trace attack chains that end in account takeover
- see what a prompt-injected Bedrock agent can reach
- measure the blast radius of one role from a saved report
- grab the AWS CLI and Terraform fix for each finding
- audit a sample account before touching production credentials
Example prompts for the agent
- Scan my AWS account for IAM escalation paths and walk me through the attack chains
- What can the hijacked
support-botagent reach? Runagent-blastwith simulator proof - Work out the blast radius of
arn:aws:iam::123456789012:role/support-bot-ticket-rolefromdemo.json
How to install cloud-audit
Platform CLI
claude mcp add cloud-audit -- uvx cloud-audituvx runs the command named after the package; if the README names another one, use uvx --from cloud-audit <command>
Platform CLI
codex mcp add cloud-audit -- uvx cloud-audituvx runs the command named after the package; if the README names another one, use uvx --from cloud-audit <command>
Config file
{
"mcpServers": {
"cloud-audit": {
"command": "uvx",
"args": [
"cloud-audit"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from cloud-audit <command>
Config file
{
"servers": {
"cloud-audit": {
"type": "stdio",
"command": "uvx",
"args": [
"cloud-audit"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from cloud-audit <command>
Platform CLI
gemini mcp add cloud-audit uvx cloud-audituvx runs the command named after the package; if the README names another one, use uvx --from cloud-audit <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about cloud-audit
How do I install cloud-audit in Claude Code?
Run claude mcp add cloud-audit -- uvx cloud-audit. That registers the server as cloud-audit and starts it with uvx.
What does cloud-audit do?
It scans an AWS account read-only for weak IAM setup, attack chains and what a hijacked AI agent can reach. Fixes for AWS CLI and Terraform ship with the findings.
What do I need before a real scan?
AWS credentials for the target account. The AWS-managed SecurityAudit policy covers all of the checks, and demo mode runs with no account at all.
