update_memory_importance · AgentCortex MCP: Risk & Policy

WHAT IT DOES

What update_memory_importance does on AgentCortex MCP

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

WHY IT NEEDS A POLICY

Why update_memory_importance needs a policy

This tool modifies existing memory records by changing their importance/priority levels. While it does not create new data (Write creation) or delete data (Destructive), it does alter the state of existing information in a reversible manner.

From the tool's definition The tool description explicitly states it updates 'the importance level of an existing memory' and allows prioritizing or de-prioritizing content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_memory_importance Rate-limited

update_memory_importance 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": {
    "update_memory_importance": {
      "limits": [
        {
          "counter": "update_memory_importance_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 AgentCortex MCP, so you can run agents against it safely.

FAQ

Questions about update_memory_importance

What does the update_memory_importance tool do? +

Update the importance level of an existing memory. Use this to prioritize critical information or de-prioritize outdated content. It is categorised as a Write tool in the AgentCortex 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 update_memory_importance? +

Register the AgentCortex MCP server in PolicyLayer and add a rule for update_memory_importance: 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 AgentCortex MCP. Nothing to install.

What risk level is update_memory_importance? +

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

Can I rate-limit update_memory_importance? +

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

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

update_memory_importance is provided by the AgentCortex MCP server (sage-hq/agentcortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

update_memory_importance is one line of AgentCortex's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →