Low Risk

view_html_log

Retrieves and displays HTML log files generated by Nova Act browser sessions. These logs contain detailed information about browser interactions, including screenshots and executed actions. Provide either a session_id to automatically find the most recent HTML log for that session, or html_path t...

How to control view_html_log ↓

What view_html_log does on Nova Act

AI agents call view_html_log to retrieve information from Nova Act without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why view_html_log needs a policy

This tool performs data retrieval only (Read category). Although it exposes detailed logs including screenshots and browser interaction history—information that could be sensitive—the tool itself has no destructive, write, execute, or financial impact.

From the tool's definition Tool description states 'Retrieves and displays HTML log files' — a read operation that queries existing data without modification. The tool accepts session_id or html_path parameters to locate and return log contents.

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

How to control view_html_log

PolicyLayer is an MCP gateway — it sits between your AI agents and Nova Act, and nothing reaches the server without passing your rules. This is the rule we recommend for view_html_log:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "view_html_log": {}
  }
}

view_html_log is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Nova Act — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about view_html_log

What does the view_html_log tool do? +

Retrieves and displays HTML log files generated by Nova Act browser sessions. These logs contain detailed information about browser interactions, including screenshots and executed actions. Provide either a session_id to automatically find the most recent HTML log for that session, or html_path to directly specify a log file path. It is categorised as a Read tool in the Nova Act MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on view_html_log? +

Register the Nova Act MCP server in PolicyLayer and add a rule for view_html_log: 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 Nova Act. Nothing to install.

What risk level is view_html_log? +

view_html_log is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit view_html_log? +

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

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

view_html_log is provided by the Nova Act MCP server (madtank/nova-act-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Nova Act tool call.

Start from Nova Act, 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.

9 Nova Act tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.