Replace the characters of a Figma text node. If nodeId is omitted, uses the first selected node.
AI agents use figma_set_text to create or update resources in MC Figma Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MC Figma Bridge environment.
This tool creates or modifies data (text content in a Figma document) in a reversible manner. The change can be undone through Figma's undo functionality, and the operation does not delete or permanently destroy data.
From the tool's definition Tool description states it will 'Replace the characters of a Figma text node', which is a modification operation. The server description confirms it 'modifies canvas elements like text and frames'.
Attacks that exploit this kind of access
Replace the characters of a Figma text node. If nodeId is omitted, uses the first selected node. It is categorised as a Write tool in the MC Figma Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MC Figma Bridge MCP server in PolicyLayer and add a rule for figma_set_text: 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 MC Figma Bridge. Nothing to install.
figma_set_text 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 figma_set_text 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 figma_set_text. 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.
figma_set_text is provided by the MC Figma Bridge MCP server (mochammad123/mcp-figma). 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 →