AI agents invoke telescope_goto_object to trigger actions in Ascom. 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.
This tool triggers a physical operation on external hardware (slewing a telescope), which is an external action with real-world effects. It is not merely reading data, nor is it destructive or financial. It fits Execute because it drives a physical device based on arguments (the target celestial object), and misuse could cause mechanical damage or collisions depending on telescope environment.
From the tool's definition Slew telescope to a named celestial object
Attacks that exploit this kind of access
Slew telescope to a named celestial object. It is categorised as a Execute tool in the Ascom MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ascom MCP server in PolicyLayer and add a rule for telescope_goto_object: 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 Ascom. Nothing to install.
telescope_goto_object 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 telescope_goto_object 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 telescope_goto_object. 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.
telescope_goto_object is provided by the Ascom MCP server (stellarpunk/mcp-server-ascom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →