AI agents call get_emotion_vocab to retrieve information from Jikan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves vocabulary data without side effects. Although the data is described as 'private,' reading private data is still a Read operation (not Write, Execute, Destructive, or Financial). The low severity reflects that vocabulary data has minimal blast radius if exposed or misused.
From the tool's definition Tool is described as 'Load the agent's full private vocabulary' — a retrieval operation with no modification, deletion, or execution of external commands. The verb 'load' indicates a read-only query.
Attacks that exploit this kind of access
Load the agent's full private vocabulary. Call once at session start. It is categorised as a Read tool in the Jikan MCP Server, which means it retrieves data without modifying state.
Register the Jikan MCP server in PolicyLayer and add a rule for get_emotion_vocab: 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 Jikan. Nothing to install.
get_emotion_vocab 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_emotion_vocab 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_emotion_vocab. 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_emotion_vocab is provided by the Jikan MCP server (thunderrabbit/jikan). 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 →