Invite a peer to a private state. The peer must be online and connected. Get the peer
AI agents use state_invite 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.
This tool creates or initiates a new invitation record in the decentralized P2P system, modifying the state of peer relationships and group membership. It is reversible (invitations can be declined or revoked) and does not delete data or execute arbitrary code. The main risk is social engineering or unauthorized group creation if an agent is compromised, hence medium severity.
From the tool's definition Invite a peer to a private state. The peer must be online and connected.
Attacks that exploit this kind of access
Invite a peer to a private state. The peer must be online and connected. Get the peer. 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.
Register the Networkselfmd MCP server in PolicyLayer and add a rule for state_invite: 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.
state_invite is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the state_invite 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.
Set action: deny in the PolicyLayer policy for state_invite. 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.
state_invite 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →