graph_audit · Graph-Memory MCP: Risk & Policy

WHAT IT DOES

What graph_audit does on Graph-Memory

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

WHY IT NEEDS A POLICY

Why graph_audit needs a policy

The tool appends (writes) a structured event to an audit log file. This is a write operation — it creates new log entries — but does not delete, execute code, or involve financial transactions. The blast radius is low since it only adds to a log file, and audit logs are generally append-only by design, making misuse relatively benign (log spam at worst).

From the tool's definition Append a structured event to the dream process audit log (logs/dream-audit.jsonl)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

graph_audit Rate-limited

graph_audit 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": {
    "graph_audit": {
      "limits": [
        {
          "counter": "graph_audit_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 Graph-Memory, so you can run agents against it safely.

FAQ

Questions about graph_audit

What does the graph_audit tool do? +

Append a structured event to the dream process audit log (logs/dream-audit.jsonl). It is categorised as a Write tool in the Graph-Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on graph_audit? +

Register the Graph-Memory MCP server in PolicyLayer and add a rule for graph_audit: 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 Graph-Memory. Nothing to install.

What risk level is graph_audit? +

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

Can I rate-limit graph_audit? +

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

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

graph_audit is provided by the Graph-Memory MCP server (stevepridemore/graph-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.