アバターに感情表現をさせるツール。
AI agents invoke emotion to trigger actions in PVV MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool triggers an external operation — causing an avatar to perform an emotional expression — which constitutes executing an action on an external system. The description is minimal and in Japanese, limiting confidence. It does not clearly read, write, or delete data, and most closely resembles an Execute action (triggering avatar behavior via the VOICEVOX/avatar system).
From the tool's definition "アバターに感情表現をさせるツール" (Tool that makes an avatar express emotions)
Attacks that exploit this kind of access
アバターに感情表現をさせるツール。. It is categorised as a Execute tool in the PVV MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PVV MCP Server MCP server in PolicyLayer and add a rule for emotion: 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 PVV MCP Server. Nothing to install.
emotion is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the emotion 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 emotion. 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.
emotion is provided by the PVV MCP Server MCP server (lambda-tuber/pvv-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 →