start_preview

THE RISK

High Risk

Why start_preview needs a policy

This tool triggers execution of the Hugo development server, which is a subprocess/external operation. While it does not modify data or delete anything, it does initiate a running process whose behavior depends on the Hugo configuration and arguments. This is Execute rather than Read, since Read tools only query/retrieve information without triggering external processes.

From the tool's definition 'Start Hugo local server for preview' — the tool executes a local server process, which is an external operation with side effects (opens a network port, runs Hugo in server mode).

Documented attack patterns abuse exactly the kind of access start_preview gives an agent:

POLICY

How to control start_preview

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 start_preview:

policy.json

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

start_preview 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.

Create a free account and register Hugo — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Hugo tools

Execute build_site Build the Hugo site for production Execute deploy_site Deploy a Hugo site to various platforms Execute stop_preview Stop a running Hugo preview server Execute install_theme Install a Hugo theme Write create_post Create a new Hugo post Write create_site Create a new Hugo site Write update_theme Update an installed Hugo theme Read check_git_installation Check if Git is installed and get its configuration

All 15 Hugo tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Hugo → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about start_preview

What does the start_preview tool do? +

Start Hugo local server for preview. 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.

How do I enforce a policy on start_preview? +

Register the Hugo MCP server in PolicyLayer and add a rule for start_preview: 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.

What risk level is start_preview? +

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

Can I rate-limit start_preview? +

Yes. Add a rate_limit block to the start_preview 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 start_preview completely? +

Set action: deny in the PolicyLayer policy for start_preview. 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 start_preview? +

start_preview 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.

Enforce policy on every Hugo tool call.

Start from Hugo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →