reflect · Codewatch Memory MCP: Risk & Policy

WHAT IT DOES

What reflect does on Codewatch Memory

AI agents invoke reflect to trigger actions in Codewatch Memory. 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 reflect needs a policy

This is classified as Execute rather than Write because it triggers an autonomous agent process whose exact effects depend on the agent's logic and the current state of observations—similar to running a script or batch operation. The severity is medium because while it modifies stored data, the modifications are reversible (observations are compressed, not deleted) and confined to a single project's memory store.

From the tool's definition The tool 'reflect' manually triggers the Reflector agent to perform compression and consolidation of observations stored in the SQLite database.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reflect Rate-limited

reflect 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": {
    "reflect": {
      "limits": [
        {
          "counter": "reflect_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 Codewatch Memory, so you can run agents against it safely.

FAQ

Questions about reflect

What does the reflect tool do? +

Manually trigger the Reflector agent to compress and consolidate observations. It is categorised as a Execute tool in the Codewatch Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on reflect? +

Register the Codewatch Memory MCP server in PolicyLayer and add a rule for reflect: 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 Codewatch Memory. Nothing to install.

What risk level is reflect? +

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

Can I rate-limit reflect? +

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

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

reflect is provided by the Codewatch Memory MCP server (klausandrade/codewatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.