Capture the current 3D preview and return it as an image so you can visually inspect the model and iterate. Optionally specify width/height.
AI agents call screenshot to retrieve information from BlockbenchMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns visual data (screenshot) from the current state of Blockbench. It does not create, modify, delete, or execute any operations that change the model or trigger external actions. It is purely informational, similar to a 'get' or 'fetch' operation, making it a Read category tool with low severity risk.
From the tool's definition Tool description states 'Capture the current 3D preview and return it as an image' — a retrieval operation with no side effects. No modifications to the model, textures, or project state occur.
Attacks that exploit this kind of access
Capture the current 3D preview and return it as an image so you can visually inspect the model and iterate. Optionally specify width/height. It is categorised as a Read tool in the BlockbenchMCP MCP Server, which means it retrieves data without modifying state.
Register the Blockbench MCP server in PolicyLayer and add a rule for 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 BlockbenchMCP. Nothing to install.
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 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 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.
screenshot is provided by the Blockbench MCP server (sosadly/blockbench-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 →