AI agents invoke BashCommand to trigger actions in Mcp Wcgw. 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.
This tool directly executes arbitrary shell commands, which is a classic Execute category risk. The ability to run any CLI command (compile, type-check, lint, invoke git, etc.) means an AI agent could execute malicious code, modify system state, exfiltrate data, or compromise the host.
From the tool's definition Tool name 'BashCommand' with description 'Execute shell commands with timeout control' combined with server description stating it can 'invoke any cli command' including compiling, type checking, linting, and github cli.
Documented attack patterns abuse exactly the kind of access BashCommand gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Wcgw, and nothing reaches the server without passing your rules. This is the rule we recommend for BashCommand:
{
"version": "1",
"default": "deny",
"tools": {
"BashCommand": {
"limits": [
{
"counter": "bashcommand_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}BashCommand 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.
Execute shell commands with timeout control. It is categorised as a Execute tool in the Mcp Wcgw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Wcgw MCP server in PolicyLayer and add a rule for BashCommand: 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 Mcp Wcgw. Nothing to install.
BashCommand 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 BashCommand 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 BashCommand. 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.
BashCommand is provided by the Mcp Wcgw MCP server (rusiaaman/wcgw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Mcp Wcgw tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Mcp Wcgw tools catalogued and risk-classified — across an index of 42,500+ MCP servers.