Execute a browser extension tool. Use this to call extension tools that provide browser-level functionality like tab management, bookmarks, history, etc.
AI agents invoke call_extension_tool to trigger actions in WebMCP. 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.
This tool triggers execution of browser-level operations via a Chrome extension. While the exact effects depend on which extension tool is invoked, the capability to manage tabs, bookmarks, and access history demonstrates it can perform irreversible state changes (e.g., closing tabs, deleting bookmarks) or access sensitive browser data.
From the tool's definition Tool description states it 'Execute[s] a browser extension tool' to call 'extension tools that provide browser-level functionality like tab management, bookmarks, history, etc.' The verb 'Execute' combined with capabilities spanning tab management, bookmarks,…
Documented attack patterns abuse exactly the kind of access call_extension_tool gives an agent:
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_extension_tool:
{
"version": "1",
"default": "deny",
"tools": {
"call_extension_tool": {
"limits": [
{
"counter": "call_extension_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}call_extension_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.
Free to start. No card required.
Execute a browser extension tool. Use this to call extension tools that provide browser-level functionality like tab management, bookmarks, history, etc. 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.
Register the Web MCP server in PolicyLayer and add a rule for call_extension_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.
call_extension_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the call_extension_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.
Set action: deny in the PolicyLayer policy for call_extension_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.
call_extension_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.
Start from WebMCP, 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.
13 WebMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.