AI agents call check_session 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 queries and returns session data without modifying, deleting, or executing operations. It is a read-only operation that retrieves existing session information, fitting the 'Read' category. The low severity reflects minimal blast radius—an AI agent misusing this tool would only retrieve unwanted session details, causing no actual harm or system changes.
From the tool's definition Tool name 'check_session' and description 'Get details for a single session' indicate a retrieval operation. The description explicitly states it retrieves information ('Get details') with no mention of modifications, deletions, or side effects.
Attacks that exploit this kind of access
Get details for a single session, including elapsed_sec if active. Free (0 credits). 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 check_session: 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.
check_session 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 check_session 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 check_session. 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.
check_session 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 →