store · State Trace MCP: Risk & Policy

WHAT IT DOES

What store does on State Trace

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

WHY IT NEEDS A POLICY

Why store needs a policy

This tool creates or modifies data in a graph-native working memory store. It is a Write operation as it persists a new typed node. The description is sparse, lowering confidence slightly. Severity is medium because misuse could pollute working memory with incorrect data, affecting agent reasoning, but it is reversible in principle.

From the tool's definition 'Store a typed working-memory node' — creates/writes a new node into working memory

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

store Rate-limited

store 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": {
    "store": {
      "limits": [
        {
          "counter": "store_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 State Trace, so you can run agents against it safely.

FAQ

Questions about store

What does the store tool do? +

Store a typed working-memory node. Context may include:. It is categorised as a Write tool in the State Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on store? +

Register the State Trace MCP server in PolicyLayer and add a rule for store: 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 State Trace. Nothing to install.

What risk level is store? +

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

Can I rate-limit store? +

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

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

store is provided by the State Trace MCP server (agent-pattern-labs/state-trace). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.