AI agents invoke install_theme to trigger actions in Hugo. 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.
Installing a theme involves downloading external code and running installation commands (e.g., git clone, module downloads) that execute external operations. It modifies the local filesystem but also executes external processes to fetch and install third-party code, making Execute the most appropriate category. Misuse could introduce malicious theme code into the site.
From the tool's definition Install a Hugo theme
Documented attack patterns abuse exactly the kind of access install_theme gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hugo, and nothing reaches the server without passing your rules. This is the rule we recommend for install_theme:
{
"version": "1",
"default": "deny",
"tools": {
"install_theme": {
"limits": [
{
"counter": "install_theme_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}install_theme 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.
Install a Hugo theme. It is categorised as a Execute tool in the Hugo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hugo MCP server in PolicyLayer and add a rule for install_theme: 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 Hugo. Nothing to install.
install_theme 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 install_theme 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 install_theme. 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.
install_theme is provided by the Hugo MCP server (sunnycloudyang/hugo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hugo, 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.
15 Hugo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.