manipulate_screenshot
Manipulate a screenshot using sharp (image processing). Supports crop (extract a region), resize, and annotate (draw colored rectangles and labels to highlight areas). Use after analyze_screenshot identifies regions of interest, or to prepare focused crops for deeper analysis. Returns the process...
This record as markdown: /tools/io-github-homenshum-nodebench/manipulate-screenshot.md
What manipulate_screenshot does on Nodebench
AI agents invoke manipulate_screenshot to trigger actions in Nodebench. 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 manipulate_screenshot is rated High
This tool runs image processing operations (crop, resize, annotate) using the sharp library, which constitutes executing external code/operations on image data. It modifies and returns processed images but does not persistently store or delete data, making Execute the most appropriate category. Severity is medium as misuse could expose or alter screenshot content, but blast radius is limited.
From the tool's definition Manipulate a screenshot using sharp (image processing). Supports crop (extract a region), resize, and annotate (draw colored rectangles and labels to highlight areas). Returns the processed image as base64.
Attacks that exploit this kind of access
The rule that runs manipulate_screenshot safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manipulate_screenshot, this is the rule to start with:
manipulate_screenshot 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 Nodebench, apply this rule, and every manipulate_screenshot call is checked against it from then on.
Questions about manipulate_screenshot
Manipulate a screenshot using sharp (image processing). Supports crop (extract a region), resize, and annotate (draw colored rectangles and labels to highlight areas). Use after analyze_screenshot identifies regions of interest, or to prepare focused crops for deeper analysis. Returns the processed image as base64. Requires sharp to be installed. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for manipulate_screenshot: 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 Nodebench. Nothing to install.
manipulate_screenshot 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 manipulate_screenshot 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 manipulate_screenshot. 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.
manipulate_screenshot is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
Across the catalogue