High Risk →

capture_console

Capture console output from a web page. Accepts a URL, optional JS command to run, and duration to wait (default 4 seconds). Returns all console messages during that time.

How to control capture_console ↓

What capture_console does on Screenshot Website Fast

AI agents invoke capture_console to trigger actions in Screenshot Website Fast. 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.

High Risk

Why capture_console needs a policy

Executing arbitrary JavaScript on a web page is a code execution capability. While the blast radius is somewhat contained (limited to a single target URL and console output), an AI agent could use this to extract sensitive data, inject malicious payloads, manipulate page state, or interact with page APIs in unintended ways.

From the tool's definition The tool accepts 'optional JS command to run' on a web page, which means it executes arbitrary JavaScript code. This is evident from the description stating it can run a JS command and capture the resulting console output.

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

How to control capture_console

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "capture_console": {
      "limits": [
        {
          "counter": "capture_console_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

capture_console 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.

  1. Create a free account and register Screenshot Website Fast — 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.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about capture_console

What does the capture_console tool do? +

Capture console output from a web page. Accepts a URL, optional JS command to run, and duration to wait (default 4 seconds). Returns all console messages during that time. It is categorised as a Execute tool in the Screenshot Website Fast MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on capture_console? +

Register the Screenshot Website Fast MCP server in PolicyLayer and add a rule for capture_console: 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 Screenshot Website Fast. Nothing to install.

What risk level is capture_console? +

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

Can I rate-limit capture_console? +

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

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

capture_console is provided by the Screenshot Website Fast MCP server (just-every/mcp-screenshot-website-fast). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Screenshot Website Fast tool call.

Start from Screenshot Website Fast, 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.

4 Screenshot Website Fast 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.