Take a screenshot of the Affinity window
AI agents call affinity_screenshot to retrieve information from Affinity MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely retrieves the current visual state of the Affinity window. It performs no side effects, does not modify files, does not execute commands with unpredictable outcomes, and does not delete or move data. It is a pure read operation analogous to a 'get' or 'fetch' query.
From the tool's definition Tool name is 'affinity_screenshot' and description states 'Take a screenshot of the Affinity window' — captures visual state of the application without modifying data or triggering external operations.
Attacks that exploit this kind of access
Take a screenshot of the Affinity window. It is categorised as a Read tool in the Affinity MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Affinity MCP Server MCP server in PolicyLayer and add a rule for affinity_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 Affinity MCP Server. Nothing to install.
affinity_screenshot 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 affinity_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 affinity_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.
affinity_screenshot is provided by the Affinity MCP Server MCP server (sekharmalla/affinity-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 →