update_state · Decision State MCP: Risk & Policy

WHAT IT DOES

What update_state does on Decision State MCP

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

WHY IT NEEDS A POLICY

Why update_state needs a policy

The tool creates or modifies data (state.json) in a reversible manner. It does not execute code or commands, does not permanently delete data, and does not involve financial transactions. This fits the Write category. Severity is medium because state corruption could affect decision-making logic, but the modification is limited to a single configuration/state file rather than production systems or irreplaceable data.

From the tool's definition Tool description states 'Apply a JSON merge patch to state.json and record why the state changed.' This modifies existing data (via merge patch) rather than deleting it. The operation is reversible through subsequent patches or resets.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_state Rate-limited

update_state 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_state": {
      "limits": [
        {
          "counter": "update_state_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 Decision State MCP, so you can run agents against it safely.

FAQ

Questions about update_state

What does the update_state tool do? +

Apply a JSON merge patch to state.json and record why the state changed. It is categorised as a Write tool in the Decision State 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_state? +

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

What risk level is update_state? +

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

Can I rate-limit update_state? +

Yes. Add a rate_limit block to the update_state 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_state completely? +

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

update_state is provided by the Decision State MCP server (koolercat/mcp-state). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.