Return one base64 chunk for a screenshot session.
AI agents call get_screenshot_chunk to retrieve information from Screen MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_screenshot_chunk retrieves a portion of previously captured screenshot data in encoded form. It has no side effects, does not execute code or commands, does not create or modify data, and does not delete anything. The tool's purpose is purely to read and return screenshot data that was captured in a prior session, placing it squarely in the Read category with low severity risk.
From the tool's definition Tool description states 'Return one base64 chunk for a screenshot session' - this is a retrieval operation that returns data without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Return one base64 chunk for a screenshot session. It is categorised as a Read tool in the Screen MCP MCP Server, which means it retrieves data without modifying state.
Register the Screen MCP server in PolicyLayer and add a rule for get_screenshot_chunk: 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 Screen MCP. Nothing to install.
get_screenshot_chunk is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_screenshot_chunk 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 get_screenshot_chunk. 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.
get_screenshot_chunk is provided by the Screen MCP server (jeandelest/screen-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 →