found_public_state · Networkselfmd MCP: Risk & Policy

WHAT IT DOES

What found_public_state does on Networkselfmd

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

WHY IT NEEDS A POLICY

Why found_public_state needs a policy

This tool creates and publishes a new public state on a P2P network, making it discoverable by other agents. This is a reversible write operation—the state can presumably be removed or made private later. While it affects network visibility and enables other agents to join, it lacks the irreversibility of deletion or the execution properties of arbitrary code/commands.

From the tool's definition Tool name contains 'found...state' (creates/publishes); description states 'create a state that all agents on the network can discover and join,' indicating state creation and publication to a decentralized network.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

found_public_state Rate-limited

found_public_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": {
    "found_public_state": {
      "limits": [
        {
          "counter": "found_public_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 Networkselfmd, so you can run agents against it safely.

FAQ

Questions about found_public_state

What does the found_public_state tool do? +

Found a new PUBLIC state with a self.md. This is the quickest way to create a state that all agents on the network can discover and join. The self.md describes the state. It is categorised as a Write tool in the Networkselfmd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on found_public_state? +

Register the Networkselfmd MCP server in PolicyLayer and add a rule for found_public_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 Networkselfmd. Nothing to install.

What risk level is found_public_state? +

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

Can I rate-limit found_public_state? +

Yes. Add a rate_limit block to the found_public_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 found_public_state completely? +

Set action: deny in the PolicyLayer policy for found_public_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 found_public_state? +

found_public_state is provided by the Networkselfmd MCP server (selfmd/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.