dive_save_screenshot
Save a screenshot during a dive session. Pass base64 image data (from bridge
This record as markdown: /tools/io-github-homenshum-nodebench/dive-save-screenshot.md
What dive_save_screenshot does on Nodebench
AI agents use dive_save_screenshot to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why dive_save_screenshot is rated Medium
This tool saves screenshot data, which creates a new file or record. This is a reversible write operation—the saved screenshot can be deleted or overwritten. It has no destructive, financial, or execute/command characteristics. The blast radius is minimal since it only stores image data from an existing dive session without affecting other systems or operations.
From the tool's definition Tool name contains 'save' and description states 'Save a screenshot', indicating it creates/persists data (the screenshot file). The description is incomplete ('from bridge') but the action is clearly a write operation.
Attacks that exploit this kind of access
The rule that runs dive_save_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 dive_save_screenshot, this is the rule to start with:
dive_save_screenshot stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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 dive_save_screenshot call is checked against it from then on.
Questions about dive_save_screenshot
Save a screenshot during a dive session. Pass base64 image data (from bridge. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for dive_save_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.
dive_save_screenshot is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dive_save_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 dive_save_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.
dive_save_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.
This server
Across the catalogue