AI agents use gsd_sketch to create or update resources in Gsd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gsd environment.
The tool creates or generates new design content (HTML mockups) in the GSD project state. This is a Write operation because it produces new data/artifacts that can be modified or deleted later. Severity is low because HTML mockups are ephemeral design artifacts with minimal blast radius if generated maliciously—they cannot affect production systems, user data, or cause financial harm.
From the tool's definition Tool description states 'sketch UI/design ideas with HTML mockups', indicating it creates new design artifacts (Write category). The action is reversible and non-destructive.
Attacks that exploit this kind of access
Rapidly sketch UI/design ideas with HTML mockups. It is categorised as a Write tool in the Gsd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gsd MCP server in PolicyLayer and add a rule for gsd_sketch: 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 Gsd. Nothing to install.
gsd_sketch 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 gsd_sketch 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 gsd_sketch. 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.
gsd_sketch is provided by the Gsd MCP server (m0-ar/gsd-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 →