AI agents call get_reactions to retrieve information from MCP Figma without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing reaction data from Figma prototypes. It performs a read-only operation with no capability to create, modify, delete, or execute changes. The blast radius of misuse is minimal since it only exposes existing design metadata. The description appears truncated ('CRITICAL: The output MUST be processed using the...') but the functional purpose remains clearly a retrieval operation.
From the tool's definition Tool name 'get_reactions' and description 'Get Figma Prototyping Reactions from multiple nodes' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get Figma Prototyping Reactions from multiple nodes. CRITICAL: The output MUST be processed using the. It is categorised as a Read tool in the MCP Figma MCP Server, which means it retrieves data without modifying state.
Register the MCP Figma MCP server in PolicyLayer and add a rule for get_reactions: 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 MCP Figma. Nothing to install.
get_reactions 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_reactions 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_reactions. 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_reactions is provided by the MCP Figma MCP server (yelowflash09/figma_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 →