Run Composer commands inside the php-fpm container
AI agents invoke warden_composer to trigger actions in Warden Magento MCP Server. 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.
Composer commands execute within a containerized environment and can modify project dependencies, install arbitrary packages, and trigger custom installation scripts. While not inherently destructive (changes are theoretically reversible), the execution context and potential for installing malicious or incompatible packages creates significant risk.
From the tool's definition Tool enables running arbitrary Composer commands inside a container. Composer is a package manager that can install, update, and modify project dependencies with significant side effects on the codebase and environment.
Documented attack patterns abuse exactly the kind of access warden_composer gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Warden Magento MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for warden_composer:
{
"version": "1",
"default": "deny",
"tools": {
"warden_composer": {
"limits": [
{
"counter": "warden_composer_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} warden_composer 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 Composer commands inside the php-fpm container. It is categorised as a Execute tool in the Warden Magento MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Warden Magento MCP Server MCP server in PolicyLayer and add a rule for warden_composer: 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 Warden Magento MCP Server. Nothing to install.
warden_composer 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 warden_composer 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 warden_composer. 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.
warden_composer is provided by the Warden Magento MCP Server MCP server (run-as-root/warden-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Warden Magento MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 Warden Magento MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.