sadd · Redis MCP Server MCP: Risk & Policy

WHAT IT DOES

What sadd does on Redis MCP Server

AI agents use sadd to create or update resources in Redis MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Redis MCP Server environment.

WHY IT NEEDS A POLICY

Why sadd needs a policy

The sadd tool adds members to a Redis set, which is a reversible write operation—the added value can be removed or modified. This is not destructive (deletion/purging), not execute (arbitrary code), and not financial. The medium severity reflects that misuse could corrupt or pollute data in Redis, but the impact is limited to the specific set and remains reversible via subsequent delete or update operations.

From the tool's definition Tool performs 'Add a value to a Redis set', which creates or modifies data in Redis. The description explicitly mentions adding values and supports an optional expiration time parameter, indicating state mutation without permanent destruction.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sadd Rate-limited

sadd stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sadd": {
      "limits": [
        {
          "counter": "sadd_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Redis MCP Server, so you can run agents against it safely.

FAQ

Questions about sadd

What does the sadd tool do? +

Add a value to a Redis set with an optional expiration time. It is categorised as a Write tool in the Redis MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sadd? +

Register the Redis MCP Server MCP server in PolicyLayer and add a rule for sadd: 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 Server. Nothing to install.

What risk level is sadd? +

sadd is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sadd? +

Yes. Add a rate_limit block to the sadd 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.

How do I block sadd completely? +

Set action: deny in the PolicyLayer policy for sadd. 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.

What MCP server provides sadd? +

sadd is provided by the Redis MCP Server MCP server (yuchenhui/mcp-redis). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.