Skip to main content
Glama
WhiteNightShadow

camoufox-reverse-mcp

click

Click on a page element using a CSS selector to enable dynamic interaction during JavaScript reverse engineering and debugging.

Instructions

Click on a page element.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
selectorYes

Implementation Reference

  • The click tool handler - takes a CSS selector, gets the active page from BrowserManager, and uses Playwright's page.click() to perform the click.
    @mcp.tool()
    async def click(selector: str) -> dict:
        """Click on a page element."""
        try:
            page = await browser_manager.get_active_page()
            await page.click(selector)
            return {"status": "clicked", "selector": selector}
        except Exception as e:
            return {"error": str(e)}
  • Registration via @mcp.tool() decorator - the 'mcp' FastMCP instance is imported from server.py and the @mcp.tool() decorator on line 313 registers the click function as an MCP tool.
    import json as _json
    import os
    
    from ..server import mcp, browser_manager
  • BrowserManager.get_active_page helper used by the click handler to retrieve the current page instance.
    async def get_active_page(self) -> Page:
        """Get the currently active page, launching the browser if needed."""
        await self._ensure_browser()
        if self.active_page_name and self.active_page_name in self.pages:
            return self.pages[self.active_page_name]
        raise RuntimeError("No active page available. Call launch_browser first.")
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. Description does not disclose any behavioral traits: waits, scrolling, error handling, return value, or side effects. The agent cannot infer if the tool blocks, throws on missing elements, or modifies page state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise but lacking structure. No front-loading of critical info. It is acceptable for a simple tool but could be improved with bullet points or warnings.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is extremely sparse. It does not cover prerequisites (page loaded, element exists), behavioral context (will it scroll to element?), or return values. For a destructive action like click, more completeness is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has a single required parameter 'selector' with no description (0% schema coverage). The tool description does not explain what format the selector expects (CSS, XPath, etc.). No additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb+resource ('Click on a page element.'). The action is evident, but does not explicitly distinguish from siblings (e.g., type_text, navigate). The description is straightforward but could be more specific (e.g., 'by CSS selector').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like type_text or evaluate_js. The description lacks context for choosing click over other interaction tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/WhiteNightShadow/camoufox-reverse-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server