AI agents use set_remove 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.
set_remove modifies Redis set data by removing members, which is a reversible write operation—the data can be re-added. This is distinct from destructive operations like db_flush or permanent deletions. Severity is medium because careless removal of set members could lose important data, but the impact is localized to a single set rather than the entire database.
From the tool's definition Tool name 'set_remove' and description '移除集合成员' (remove set members) indicate reversible modification of set data structures in Redis.
Attacks that exploit this kind of access
移除集合成员. 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 set_remove: 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.
set_remove 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 set_remove 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 set_remove. 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.
set_remove 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 →