bad-ass-mcp

Overview Schema Source Related Servers Discussions Admin

click_at

Click absolute screen coordinates to reach webviews, canvas, and custom-drawn UI that accessibility-based clicking misses. Supports left, right, and middle buttons, single or double clicks.

Instructions

Click at absolute screen coordinates (top-left origin, in points).

button: "left" (default), "right" (context menus) or "middle". clicks: 1 (default) or 2 for a real double-click.

Fallback for when accessibility-based clicking can't reach a target: webview content (Tauri/Electron/CEF), custom-drawn UI, OpenGL/canvas, etc.

Delivery is system-global (kCGHIDEventTap on macOS) so the click actually reaches webviews. This was a regression in the first version, which used PID-targeted delivery that silently no-op'd on webview content while still returning ok. The cost is that the click affects whatever window is at (x, y), so make sure the target window is on top first.

window_id is advisory only: the call cannot verify delivery, just that the events were posted.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "x": "<x>",
      "y": "<y>"
    },
    "name": "click_at"
  }
}

Input Schema

Name	Required	Default
`x`	Yes
`y`	Yes
`button`	No	left
`clicks`	No
`window_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 13, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: it discloses system-global delivery via kCGHIDEventTap, warns that the click lands on whatever window is at (x, y), and states that window_id is advisory and delivery cannot be verified. It even explains a past failure mode where PID-targeted delivery silently no-op'd while returning ok, which directly informs trust in the result.

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

Conciseness4/5

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

Core facts (coordinates, modifiers, fallback rationale) are front-loaded and each bullet earns its place. The historical regression anecdote is slightly long-winded, but it justifies the system-global design and the verification caveat, so it is not wasted.

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

Completeness4/5

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

For a five-parameter, no-annotation, no-output-schema tool, this covers coordinate semantics, modifiers, delivery scope, and the limits of the success signal. The only soft spot is error behavior, such as what happens with off-screen or invalid coordinates, which is left unstated.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does: x/y are absolute points from top-left, button enumerates left/right/middle with the context-menu hint for right, clicks explains that 2 means a real double-click, and window_id is explicitly labeled advisory-only. All five parameters gain meaning beyond the bare schema titles.

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

Purpose5/5

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

States a specific verb and resource (click at absolute screen coordinates) and immediately pins down the coordinate system as top-left origin in points. It also distinguishes itself from the accessibility-based clicking path, so an agent can tell it apart from the sibling 'click' tool without opening either schema.

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

Usage Guidelines4/5

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

Gives concrete when-to-use conditions (webview content in Tauri/Electron/CEF, custom-drawn UI, OpenGL/canvas) and frames itself as a fallback, which implies accessibility-based clicking is preferred. It adds a prerequisite (target window must be on top). The gap is that the preferred alternative is not named as a sibling tool, so the routing is conceptual rather than explicit.

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

Deploy Server