AI agents invoke run-aws-code to trigger actions in Aws. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The ability to 'run' code in an AWS environment is an Execute-category risk. Given the sibling tools provide credential and profile selection, an AI agent could execute malicious AWS API calls, deploy resources, exfiltrate data, or cause widespread infrastructure damage. The blast radius is critical — an attacker or misaligned agent could compromise the entire AWS account.
From the tool's definition Tool name 'run-aws-code' with description 'Run AWS code' indicates execution of arbitrary code within AWS environment.
Documented attack patterns abuse exactly the kind of access run-aws-code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Aws, and nothing reaches the server without passing your rules. This is the rule we recommend for run-aws-code:
{
"version": "1",
"default": "deny",
"tools": {
"run-aws-code": {
"limits": [
{
"counter": "run-aws-code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run-aws-code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run AWS code. It is categorised as a Execute tool in the Aws MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Aws MCP server in PolicyLayer and add a rule for run-aws-code: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Aws. Nothing to install.
run-aws-code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run-aws-code rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run-aws-code. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run-aws-code is provided by the Aws MCP server (rafalwilinski/aws-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Aws tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Aws tools catalogued and risk-classified — across an index of 42,500+ MCP servers.