AI agents use zset_add to create or update resources in Redis MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Redis MCP environment.
This tool creates or modifies data in Redis sorted sets by adding members. Write operations can be reversed (members can be deleted), so this is categorized as Write rather than Destructive. Severity is medium because misuse could corrupt application data or consume resources, but the impact is typically reversible and limited to a single data structure unless combined with other operations.
From the tool's definition Tool name 'zset_add' and description '添加有序集合成员' (add sorted set member) indicate creation/modification of data in a Redis sorted set.
Attacks that exploit this kind of access
添加有序集合成员. It is categorised as a Write tool in the Redis MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Redis MCP server in PolicyLayer and add a rule for zset_add: 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 Redis MCP. Nothing to install.
zset_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the zset_add 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 zset_add. 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.
zset_add is provided by the Redis MCP server (pickstar-2002/redis-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 →