peer_trust · Networkselfmd MCP: Risk & Policy

WHAT IT DOES

What peer_trust does on Networkselfmd

AI agents use peer_trust 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 peer_trust needs a policy

The tool modifies local state by setting a trust flag on a peer. It is reversible (trust can be revoked), affects only local data with no network-side effects, and has minimal blast radius — at worst, an agent could incorrectly trust a malicious peer, but the change itself is local and likely reversible.

From the tool's definition Mark a peer as trusted... This is a local flag only

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

peer_trust Rate-limited

peer_trust 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": {
    "peer_trust": {
      "limits": [
        {
          "counter": "peer_trust_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 peer_trust

What does the peer_trust tool do? +

Mark a peer as trusted. Trusted peers are highlighted in the dashboard. This is a local flag only — it doesn. 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 peer_trust? +

Register the Networkselfmd MCP server in PolicyLayer and add a rule for peer_trust: 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 peer_trust? +

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

Can I rate-limit peer_trust? +

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

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

peer_trust 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.