Navigate forward in browser history
AI agents invoke go_forward to trigger actions in Webclaw. 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 a browser navigation action, which is an external operation that changes the browser state. While navigating forward in history is generally benign and reversible (you can go back), it is still an Execute-category action as it controls the browser and can load pages with side effects depending on what page is navigated to.
From the tool's definition Navigate forward in browser history
Documented attack patterns abuse exactly the kind of access go_forward gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Webclaw, and nothing reaches the server without passing your rules. This is the rule we recommend for go_forward:
{
"version": "1",
"default": "deny",
"tools": {
"go_forward": {
"limits": [
{
"counter": "go_forward_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}go_forward 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.
Navigate forward in browser history. It is categorised as a Execute tool in the Webclaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Webclaw MCP server in PolicyLayer and add a rule for go_forward: 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 Webclaw. Nothing to install.
go_forward 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 go_forward 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 go_forward. 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.
go_forward is provided by the Webclaw MCP server (kuroko1t/webclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Webclaw, 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.
21 Webclaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.