AI agents call chronica_get_last_seen to retrieve information from Chronica without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves a single timestamp value from a specified thread type. It queries state without modifying, creating, deleting, or executing any operations. This is a straightforward Read category action with minimal blast radius if misused—at worst, an agent could log irrelevant timestamps.
From the tool's definition Tool name 'chronica_get_last_seen' and description indicate retrieval of timestamp metadata ('最後に見た時刻を取得します' = 'get the last seen time'). This is a query operation with no side effects.
Attacks that exploit this kind of access
指定されたスレッドタイプで最後に見た時刻を取得します。. It is categorised as a Read tool in the Chronica MCP Server, which means it retrieves data without modifying state.
Register the Chronica MCP server in PolicyLayer and add a rule for chronica_get_last_seen: 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 Chronica. Nothing to install.
chronica_get_last_seen 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 chronica_get_last_seen 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 chronica_get_last_seen. 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.
chronica_get_last_seen is provided by the Chronica MCP server (nic9dev/chronica). 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 →