AI agents invoke screenshot_one_liner to trigger actions in ShotAPI. 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.
The tool name suggests it captures a screenshot in a single call, similar to the sibling 'screenshot' tool. Screenshots involve triggering an external browser/rendering operation, which qualifies as Execute. However, the description is empty, lowering confidence.
From the tool's definition Tool name 'screenshot_one_liner' on a server described as handling 'screenshot' and 'render' operations; sibling tools are 'render' and 'screenshot'.
Attacks that exploit this kind of access
screenshot_one_liner. It is categorised as a Execute tool in the ShotAPI MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ShotAPI MCP server in PolicyLayer and add a rule for screenshot_one_liner: 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 ShotAPI. Nothing to install.
screenshot_one_liner 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 screenshot_one_liner 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 screenshot_one_liner. 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.
screenshot_one_liner is provided by the ShotAPI MCP server (smallhandsome/shotapi-mcp-server). 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 →