call_website_tool

THE RISK

High Risk

Why call_website_tool needs a policy

This tool executes website-provided JavaScript functions with effects determined by the argument (which tool to call). While not inherently destructive, it can trigger any operation a website exposes—from reading data to making requests, depending on what tools are registered.

From the tool's definition Tool description states 'Execute a tool from a website MCP server' and context indicates it allows AI agents to 'interact with the browser environment.' This enables running arbitrary code/functions exposed by websites.

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

POLICY

How to control call_website_tool

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

policy.json

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

call_website_tool 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 WebMCP — 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 WebMCP tools

Destructive extension_tool_userscripts_unregister Unregister userscripts by ID or filter Execute call_extension_tool Execute a browser extension tool. Use this to call extension tools that provide browser-le Execute extension_tool_userscripts_test_execute Test execute a script without registering it (Chrome 135+) Execute extension_tool_userscripts_configure_world Configure USER_SCRIPT world properties Execute extension_tool_userscripts_register Register a new userscript with Chrome userScripts API Write extension_tool_userscripts_reset_world Reset USER_SCRIPT world configuration to defaults Write extension_tool_userscripts_update Update existing userscripts Read extension_tool_check_available_apis Check which Chrome Extension APIs are available to the extension

All 13 WebMCP 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 WebMCP → 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 call_website_tool

What does the call_website_tool tool do? +

Execute a tool from a website MCP server. Use this to call website-specific tools that you discovered via list_website_tools. It is categorised as a Execute tool in the WebMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on call_website_tool? +

Register the Web MCP server in PolicyLayer and add a rule for call_website_tool: 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 WebMCP. Nothing to install.

What risk level is call_website_tool? +

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

Can I rate-limit call_website_tool? +

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

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

call_website_tool is provided by the Web MCP server (miguelspizza/webmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every WebMCP tool call.

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

CHECK YOUR STACK →