New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

input.click_target

Left/right/middle-click a UIA target by id from the latest screen.observe (uses native center coords). Prefer over input.click_xy. Side effect: real mouse click on the remote Windows desktop. Do not reuse target_id after the screen may have changed — re-observe first. For click→type→keys sequence...

SERVERGlasswarp SOURCEhttps://mcp.glasswarp.com/mcp
High RISK CLASS
Category Execute
Parameters 42 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-glasswarp-mcp-server/input.click-target.md

What input.click_target does on Glasswarp

AI agents invoke input.click_target to trigger actions in Glasswarp. 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.

ParameterTypeRequiredDescription
button string Mouse button (default left)
double boolean If true, double-click (two clicks)
target_id string Yes Target id from the most recent screen.observe (e.g. uia-… )
session_id string Yes Active session id

Parameters from the server's own tool schema.

Why input.click_target is rated High

This tool triggers external operations (mouse clicks on a remote Windows PC) whose effects are determined by the arguments (target_id, click type). The outcome is not reversible in a general sense and depends on what application/UI state exists at execution time. While not destructive by itself, it executes user-interface actions on a live system, making it Execute category.

From the tool's definition Tool performs 'real mouse click on the remote Windows desktop' with side effects that depend on what UI element is targeted.

Questions about input.click_target

What does the input.click_target tool do? +

Left/right/middle-click a UIA target by id from the latest screen.observe (uses native center coords). Prefer over input.click_xy. Side effect: real mouse click on the remote Windows desktop. Do not reuse target_id after the screen may have changed — re-observe first. For click→type→keys sequences, use input.send_actions (one turn) instead of chaining this tool. It is categorised as a Execute tool in the Glasswarp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does input.click_target accept? +

input.click_target accepts 4 parameters: button, double, target_id, session_id. Required: target_id, session_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on input.click_target? +

Register the Glasswarp MCP server in PolicyLayer and add a rule for input.click_target: 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 Glasswarp. Nothing to install.

What risk level is input.click_target? +

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

Can I rate-limit input.click_target? +

Yes. Add a rate_limit block to the input.click_target 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 input.click_target completely? +

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

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

More on Glasswarp, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Glasswarp's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.