AI agents call suggestions 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.
This tool queries the memory system to surface recommendations for new memory entries. It reads existing query patterns and the state of stored memories to generate suggestions. There are no side effects: no data is created, modified, deleted, or executed. The worst-case misuse would be information disclosure or wasted compute on irrelevant suggestions, both low-impact outcomes.
From the tool's definition The tool 'gets suggestions' and operates 'based on queries that returned no results' — it retrieves and analyzes data without modifying, deleting, or executing external operations. The phrase 'Get suggestions' indicates a passive data retrieval action.
Attacks that exploit this kind of access
Get suggestions for memories you should store, based on queries that returned no results. 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 suggestions: 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.
suggestions 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 suggestions 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 suggestions. 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.
suggestions 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 →