This record as markdown: /tools/io-github-lokmenower-best-cad-mcp/select-on-screen.md
What select_on_screen does on Pypi:best Cad
AI agents invoke select_on_screen to trigger actions in Pypi:best Cad. 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.
Why select_on_screen is rated High
This tool triggers an interactive operation within AutoCAD, prompting the user to perform a manual selection action in the application UI. It goes beyond a pure read/query since it actively invokes an external application's interactive mode and triggers an external operation. However, it does not modify or delete data itself, placing it in the Execute category.
From the tool's definition 交互式屏幕选择 — 提示用户在 AutoCAD 中手动选择实体 (Interactive screen selection — prompts the user to manually select entities in AutoCAD)
Attacks that exploit this kind of access
The rule that runs select_on_screen safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Pypi:best Cad, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For select_on_screen, this is the rule to start with:
select_on_screen 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Pypi:best Cad, apply this rule, and every select_on_screen call is checked against it from then on.
Questions about select_on_screen
交互式屏幕选择 — 提示用户在 AutoCAD 中手动选择实体。. It is categorised as a Execute tool in the Pypi:best Cad MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pypi:best Cad MCP server in PolicyLayer and add a rule for select_on_screen: 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 Pypi:best Cad. Nothing to install.
select_on_screen 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 select_on_screen 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 select_on_screen. 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.
select_on_screen is provided by the Pypi:best Cad MCP server (pypi:best-cad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Pypi:best Cad, and thousands of servers like it.
Across the catalogue