aws_cli · Self-hosted MCP server for Claude MCP

WHAT IT DOES

What aws_cli does on Self-hosted MCP server for Claude

AI agents invoke aws_cli to trigger actions in Self-hosted MCP server for Claude. 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.

WHY IT NEEDS A POLICY

Why aws_cli needs a policy

This tool executes arbitrary AWS CLI commands with effects determined entirely by user input. While AWS CLI can read data (low risk), it equally enables destructive operations (delete resources, terminate instances), financial operations (provision expensive resources, modify billing settings), and lateral movement. The ability to 'run' commands with argument-dependent effects makes this Execute category.

From the tool's definition Tool description states 'Run an AWS CLI command' which directly executes external operations. AWS CLI commands can perform any action on AWS infrastructure depending on arguments passed.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

aws_cli Rate-limited

aws_cli 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "aws_cli": {
      "limits": [
        {
          "counter": "aws_cli_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Self-hosted MCP server for Claude, so you can run agents against it safely.

FAQ

Questions about aws_cli

What does the aws_cli tool do? +

Run an AWS CLI command using the locally configured AWS profile. Pass arguments as an array of strings (no. It is categorised as a Execute tool in the Self-hosted MCP server for Claude MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on aws_cli? +

Register the Self-hosted MCP server for Claude MCP server in PolicyLayer and add a rule for aws_cli: 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 Self-hosted MCP server for Claude. Nothing to install.

What risk level is aws_cli? +

aws_cli is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit aws_cli? +

Yes. Add a rate_limit block to the aws_cli 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.

How do I block aws_cli completely? +

Set action: deny in the PolicyLayer policy for aws_cli. 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.

What MCP server provides aws_cli? +

aws_cli is provided by the Self-hosted MCP server for Claude MCP server (leszczynskikarol/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.