Submit a screenshot capture request for a URL.
AI agents invoke capture to trigger actions in Shotbot Mcp. 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 initiates an external action (capturing a screenshot of a URL via an API), which constitutes executing an external operation. It is not purely a read since it submits a request that causes a remote service to perform work. The blast radius is medium since it could be used to probe internal/sensitive URLs or consume API credits, but it does not modify or delete data.
From the tool's definition 'Submit a screenshot capture request for a URL' — triggers an external operation (screenshot capture) against an arbitrary public URL
Attacks that exploit this kind of access
Submit a screenshot capture request for a URL. It is categorised as a Execute tool in the Shotbot Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Shotbot MCP server in PolicyLayer and add a rule for capture: 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 Shotbot Mcp. Nothing to install.
capture 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 capture 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 capture. 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.
capture is provided by the Shotbot MCP server (shotbot-mcp). 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 →