store_data · Memory Cache Server MCP: Risk & Policy

WHAT IT DOES

What store_data does on Memory Cache Server

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

WHY IT NEEDS A POLICY

Why store_data needs a policy

This tool writes data into a memory cache. It does not execute code, delete data, or involve financial transactions. The operation is reversible (data can be cleared or expires via TTL). Severity is medium because an agent could store sensitive or malicious data in the cache, potentially affecting subsequent interactions that retrieve from it.

From the tool's definition 'Store data in the cache' — creates or modifies cached data with an optional TTL (time-to-live), which is a reversible write operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

store_data Rate-limited

store_data 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": {
    "store_data": {
      "limits": [
        {
          "counter": "store_data_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 Memory Cache Server, so you can run agents against it safely.

FAQ

Questions about store_data

What does the store_data tool do? +

Store data in the cache with optional TTL. It is categorised as a Write tool in the Memory Cache 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 store_data? +

Register the Memory Cache Server MCP server in PolicyLayer and add a rule for store_data: 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 Memory Cache Server. Nothing to install.

What risk level is store_data? +

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

Can I rate-limit store_data? +

Yes. Add a rate_limit block to the store_data 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 store_data completely? +

Set action: deny in the PolicyLayer policy for store_data. 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 store_data? +

store_data is provided by the Memory Cache Server MCP server (tosin2013/mcp-memory-cache-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.