memory_benchmark · Exocortex MCP: Risk & Policy

WHAT IT DOES

What memory_benchmark does on Exocortex

AI agents invoke memory_benchmark to trigger actions in Exocortex. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why memory_benchmark needs a policy

The tool triggers execution of a benchmark suite with measurable side effects (computation, resource consumption, potentially I/O operations against the memory system). While not destructive or write-heavy, it goes beyond simple Read operations by actively executing performance evaluation logic.

From the tool's definition Tool performs 'Run a retrieval benchmark' — executes a computational operation that measures recall metrics against stored memory data. This is an active execution of a benchmark algorithm rather than passive data retrieval.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_benchmark Rate-limited

memory_benchmark stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_benchmark": {
      "limits": [
        {
          "counter": "memory_benchmark_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Exocortex, so you can run agents against it safely.

FAQ

Questions about memory_benchmark

What does the memory_benchmark tool do? +

Run a retrieval benchmark measuring recall@5, recall@10, and MRR. It is categorised as a Execute tool in the Exocortex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on memory_benchmark? +

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

What risk level is memory_benchmark? +

memory_benchmark is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit memory_benchmark? +

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

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

memory_benchmark is provided by the Exocortex MCP server (shawnhack/exocortex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.