tag_normalize_preview
AI agents call tag_normalize_preview to retrieve information from Vector Memory MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to preview the results of tag normalization (semantic inspection of memory tags) rather than modify, delete, or execute operations. It fits the Read category as a query/inspection tool.
From the tool's definition Tool name 'tag_normalize_preview' suggests a preview/read operation on tag normalization. The description is empty, limiting direct evidence, but the 'preview' suffix and naming convention imply non-destructive inspection of how tags would be normalized…
Attacks that exploit this kind of access
tag_normalize_preview. It is categorised as a Read tool in the Vector Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Vector Memory MCP server in PolicyLayer and add a rule for tag_normalize_preview: 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 Vector Memory MCP. Nothing to install.
tag_normalize_preview 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 tag_normalize_preview 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 tag_normalize_preview. 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.
tag_normalize_preview is provided by the Vector Memory MCP server (xsaven/vector-memory-mcp). 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 →