AI agents call detect_duplicates 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 is a read-only analytical operation that retrieves and analyzes memory data to compute similarity metrics. It has no side effects on the data (no creation, modification, or deletion), no code execution capabilities, and no destructive impact. The operation is informational only, making it a Read category tool with low risk.
From the tool's definition Tool performs detection/analysis of existing data ('detect_duplicates', 'using Jaccard similarity') without modifying, deleting, or executing external operations. It queries and compares stored memories to identify similarity patterns.
Attacks that exploit this kind of access
Detect near-duplicate memories using Jaccard similarity on key+value tokens. 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 detect_duplicates: 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.
detect_duplicates 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 detect_duplicates 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 detect_duplicates. 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.
detect_duplicates 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 →