Capture a screenshot of an Abaqus viewport.
AI agents call get_viewport_image to retrieve information from Codex MCP Abaqus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool captures a screenshot/image of the current state of the Abaqus GUI viewport. Screenshots are read-only operations that retrieve visual information without side effects, data modification, or triggering simulations. The blast radius of misuse is minimal—an attacker could only learn about viewport contents, not alter the simulation or execute commands.
From the tool's definition Tool name 'get_viewport_image' and description 'Capture a screenshot of an Abaqus viewport' indicate a retrieval operation that captures visual state without modifying data or triggering external operations.
Attacks that exploit this kind of access
Capture a screenshot of an Abaqus viewport. It is categorised as a Read tool in the Codex MCP Abaqus MCP Server, which means it retrieves data without modifying state.
Register the Codex MCP Abaqus MCP server in PolicyLayer and add a rule for get_viewport_image: 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 Codex MCP Abaqus. Nothing to install.
get_viewport_image 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_viewport_image 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_viewport_image. 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_viewport_image is provided by the Codex MCP Abaqus MCP server (zhangyoupeng1996/codex_mcp_abaqus). 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 →