Create a new GitHub branch for feature development.
AI agents use setup_project_branch to create or update resources in Figma to React MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Figma to React MCP environment.
Creating a branch is a reversible modification to the source control system. It does not delete data (not Destructive), does not move money (not Financial), and while it interacts with GitHub, it is fundamentally a write operation that creates a new resource. The branch can be deleted if needed.
From the tool's definition Tool description states 'Create a new GitHub branch for feature development.' The word 'Create' indicates a write operation that generates a new branch in a GitHub repository.
Attacks that exploit this kind of access
Create a new GitHub branch for feature development. It is categorised as a Write tool in the Figma to React MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Figma to React MCP server in PolicyLayer and add a rule for setup_project_branch: 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 Figma to React MCP. Nothing to install.
setup_project_branch 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 setup_project_branch 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 setup_project_branch. 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.
setup_project_branch is provided by the Figma to React MCP server (surisagar900/figma-to-react-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 →