AI agents call trends to retrieve information from Tages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool analyzes historical performance metrics to identify trends, which is fundamentally a read operation. There is no indication it modifies data, executes code, deletes information, or commits financial obligations. The capability is informational only—it retrieves and analyzes existing performance data to surface patterns.
From the tool's definition Tool name: 'trends'; description: 'Detect performance trends across sessions — improvements and regressions'. The verb 'detect' and the use of 'across sessions' indicates analysis and retrieval of stored performance data without modification.
Attacks that exploit this kind of access
Detect performance trends across sessions — improvements and regressions. It is categorised as a Read tool in the Tages MCP Server, which means it retrieves data without modifying state.
Register the Tages MCP server in PolicyLayer and add a rule for trends: 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 Tages. Nothing to install.
trends 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 trends 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 trends. 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.
trends is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →