ragionex_save_memory · Ragionex Memory MCP: Risk & Policy

WHAT IT DOES

What ragionex_save_memory does on Ragionex Memory MCP

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

WHY IT NEEDS A POLICY

Why ragionex_save_memory needs a policy

The tool creates or modifies data (facts, preferences, decisions) in a persistent memory system. It is Write rather than Read (no side effects beyond storage), not Destructive (reversible via update/delete), not Execute (does not run code or trigger external operations), and not Financial.

From the tool's definition Tool name and description explicitly state 'Save' and 'persist across sessions'; parameters enable creating and storing durable facts, preferences, and decisions in persistent storage.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ragionex_save_memory Rate-limited

ragionex_save_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": {
    "ragionex_save_memory": {
      "limits": [
        {
          "counter": "ragionex_save_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 Ragionex Memory MCP, so you can run agents against it safely.

FAQ

Questions about ragionex_save_memory

What does the ragionex_save_memory tool do? +

Save a durable fact, preference, or decision to ragionex-memory-mcp (cross-client persistent memory: Claude Desktop, Claude Code, Cursor, Cline, Codex, ChatGPT, Zed). Use for content that should persist across sessions and AI tools. Parameters:. It is categorised as a Write tool in the Ragionex Memory 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 ragionex_save_memory? +

Register the Ragionex Memory MCP server in PolicyLayer and add a rule for ragionex_save_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 Ragionex Memory MCP. Nothing to install.

What risk level is ragionex_save_memory? +

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

Can I rate-limit ragionex_save_memory? +

Yes. Add a rate_limit block to the ragionex_save_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 ragionex_save_memory completely? +

Set action: deny in the PolicyLayer policy for ragionex_save_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 ragionex_save_memory? +

ragionex_save_memory is provided by the Ragionex Memory MCP server (ragionex/memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.