browse_click

Click an element by its @eN ref from the last browse_snapshot.

SERVERGateway SOURCEhttps://wingmanprotocol.com/mcp

High RISK CLASS

Category Execute

Parameters 22 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-click.md

WHAT IT DOES

What browse_click does on Gateway

AI agents invoke browse_click to trigger actions in Gateway. 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.

Parameter	Type	Required	Description
`ref`	string	Yes	an @eN ref from browse_snapshot
`browser_id`	string	Yes	from browse_open

Parameters from the server's own tool schema.

RISK

Why browse_click is rated High

This tool performs a browser action (clicking an element) that triggers external operations whose effects depend on the target element. Clicking can submit forms, trigger purchases, navigate pages, or cause any number of side effects depending on what element is clicked — making it Execute category with high severity due to the broad and unpredictable blast radius if misused by an AI agent.

From the tool's definition Click an element by its @eN ref from the last browse_snapshot

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browse_click safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browse_click, this is the rule to start with:

browse_click Rate-limited

browse_click 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every browse_click call is checked against it from then on.

FAQ

Questions about browse_click

What does the browse_click tool do? +

Click an element by its @eN ref from the last browse_snapshot. It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does browse_click accept? +

browse_click accepts 2 parameters: ref, browser_id. Required: ref, browser_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on browse_click? +

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

What risk level is browse_click? +

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

Can I rate-limit browse_click? +

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

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

browse_click is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Gateway, and thousands of servers like it.

This server

All 271 Gateway tools → High-risk tools on this server →

Across the catalogue

browser_click on Percepta MCP Server →qt_click on Qt → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →