create_design_system
AI agents use create_design_system to create or update resources in Stitch-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Stitch-MCP environment.
The 'create_design_system' tool creates a new design system object, which is a Write operation (creates/modifies data reversibly). While the description is empty, the tool name and context of design system management on this MCP server strongly indicate data creation. Severity is medium because misuse would add unwanted design system configurations but would not irreversibly delete data or execute arbitrary code.
From the tool's definition Tool name 'create_design_system' indicates creation of a design system artifact. Sibling tools show this server manages design and project data (generate_screen_from_text, apply_design_system, edit_screens, create_project).
Attacks that exploit this kind of access
create_design_system. It is categorised as a Write tool in the Stitch-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Stitch- MCP server in PolicyLayer and add a rule for create_design_system: 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 Stitch-MCP. Nothing to install.
create_design_system 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 create_design_system 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 create_design_system. 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.
create_design_system is provided by the Stitch- MCP server (samueljayasingh/stitchmcp). 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 →