store_semantic_memory · Metis Public Health MCP

WHAT IT DOES

What store_semantic_memory does on Metis Public Health

AI agents use store_semantic_memory to create or update resources in Metis Public Health — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metis Public Health environment.

WHY IT NEEDS A POLICY

Why store_semantic_memory needs a policy

The name strongly suggests this tool writes semantic memory entries to some persistent store. Based on sibling tools like 'add_memory_entry', this fits the Write category — creating or modifying data reversibly. No description is available to confirm or refine this, so confidence is reduced. Severity is medium since storing incorrect or malicious memory entries could influence future AI responses.

From the tool's definition Tool name 'store_semantic_memory' implies writing/storing data; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

store_semantic_memory Rate-limited

store_semantic_memory 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_semantic_memory": {
      "limits": [
        {
          "counter": "store_semantic_memory_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 Metis Public Health, so you can run agents against it safely.

FAQ

Questions about store_semantic_memory

What does the store_semantic_memory tool do? +

store_semantic_memory. It is categorised as a Write tool in the Metis Public Health 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_semantic_memory? +

Register the Metis Public Health MCP server in PolicyLayer and add a rule for store_semantic_memory: 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 Metis Public Health. Nothing to install.

What risk level is store_semantic_memory? +

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

Can I rate-limit store_semantic_memory? +

Yes. Add a rate_limit block to the store_semantic_memory 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_semantic_memory completely? +

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

store_semantic_memory is provided by the Metis Public Health MCP server (sveritg/metis_ph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.