semantic_memory_add · Universal Dev MCP: Risk & Policy

WHAT IT DOES

What semantic_memory_add does on Universal Dev MCP

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

WHY IT NEEDS A POLICY

Why semantic_memory_add needs a policy

This tool creates or adds entries to a semantic memory store indexed by user_id. This is a reversible write operation—data can be modified or removed later. It does not execute arbitrary code, delete data irreversibly, or move money. The blast radius is medium: if misused by an agent, it could pollute the memory store with incorrect or malicious entries, but the damage is not irreversible and is scoped to a user_id.

From the tool's definition Tool name 'semantic_memory_add' combined with 'add' action indicates creation or modification of data. The description specifies 'user_id based' storage, suggesting persistent data creation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

semantic_memory_add Rate-limited

semantic_memory_add 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": {
    "semantic_memory_add": {
      "limits": [
        {
          "counter": "semantic_memory_add_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 Universal Dev MCP, so you can run agents against it safely.

FAQ

Questions about semantic_memory_add

What does the semantic_memory_add tool do? +

Semantic memory add (user_id based). It is categorised as a Write tool in the Universal Dev MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on semantic_memory_add? +

Register the Universal Dev MCP server in PolicyLayer and add a rule for semantic_memory_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 Universal Dev MCP. Nothing to install.

What risk level is semantic_memory_add? +

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

Can I rate-limit semantic_memory_add? +

Yes. Add a rate_limit block to the semantic_memory_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.

How do I block semantic_memory_add completely? +

Set action: deny in the PolicyLayer policy for semantic_memory_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.

What MCP server provides semantic_memory_add? +

semantic_memory_add is provided by the Universal Dev MCP server (kallusuvaidyam/universal_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.