interceptor_browser_add_script_tag

THE RISK

High Risk

Why interceptor_browser_add_script_tag needs a policy

Injecting a script tag into a live browser page executes arbitrary JavaScript in that page's context, giving full access to DOM, cookies, credentials, and network requests. This is a classic XSS/code-injection vector and represents Execute at the highest severity since an AI agent could use it to exfiltrate data, hijack sessions, or perform any action the user can perform in the browser.

From the tool's definition Append a <script> element to the current page (Playwright)

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

POLICY

How to control interceptor_browser_add_script_tag

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

policy.json

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

interceptor_browser_add_script_tag 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 Proxy — 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 Proxy tools

Destructive interceptor_docker_detach Remove proxy configuration from a Docker container and clean up injected files. Destructive proxy_clear_traffic Clear all captured traffic from the buffer. Destructive proxy_delete_session Delete a recorded session from disk. Destructive proxy_remove_host_upstream Remove a per-host upstream proxy override. Destructive proxy_remove_rule Delete an interception rule. Destructive proxy_session_stop Stop persistent on-disk capture and finalize the active session. Destructive interceptor_deactivate_all Kill ALL active interceptors across all types. Emergency cleanup — stops all browser insta Destructive interceptor_kill Kill a spawned process by target ID. Also retrieves final stdout/stderr output.

All 89 Proxy 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 Proxy → 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 interceptor_browser_add_script_tag

What does the interceptor_browser_add_script_tag tool do? +

Append a <script> element to the current page (Playwright. It is categorised as a Execute tool in the Proxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on interceptor_browser_add_script_tag? +

Register the Proxy MCP server in PolicyLayer and add a rule for interceptor_browser_add_script_tag: 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 Proxy. Nothing to install.

What risk level is interceptor_browser_add_script_tag? +

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

Can I rate-limit interceptor_browser_add_script_tag? +

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

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

interceptor_browser_add_script_tag is provided by the Proxy MCP server (yfe404/proxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Proxy tool call.

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

CHECK YOUR STACK →