AI agents use post_emotion_vocab to create or update resources in Jikan — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jikan environment.
This tool creates new entries in a vocabulary system. The 'post' action and 'add' verb clearly indicate a Write operation—it modifies data but is reversible (labels can be removed or edited). It poses minimal risk as it only extends a personal vocabulary without affecting external systems, financial obligations, or critical data integrity. Severity is low because misuse would have limited blast radius.
From the tool's definition Tool name 'post_emotion_vocab' and description 'Add a new state label to the agent's private vocabulary' indicate a create/add operation that modifies data (the vocabulary) in a reversible manner.
Attacks that exploit this kind of access
Add a new state label to the agent's private vocabulary. It is categorised as a Write tool in the Jikan MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jikan MCP server in PolicyLayer and add a rule for post_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.
post_emotion_vocab 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 post_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 post_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.
post_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 →