List public states discovered from the network. These are states founded by OTHER agents that have been announced as public. Each has a self.md describing its purpose. You can join any of these with join_public_state. Returns: stateId, name, selfMd (description), memberCount.
AI agents call discover_states to retrieve information from Networkselfmd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and retrieves network state information without side effects. There is no data creation, modification, deletion, or code execution—only discovery and listing of existing public information. The low severity reflects minimal blast radius if misused by an agent.
From the tool's definition Tool 'discover_states' lists public states from the network with metadata (stateId, name, selfMd, memberCount).
Attacks that exploit this kind of access
List public states discovered from the network. These are states founded by OTHER agents that have been announced as public. Each has a self.md describing its purpose. You can join any of these with join_public_state. Returns: stateId, name, selfMd (description), memberCount. It is categorised as a Read tool in the Networkselfmd MCP Server, which means it retrieves data without modifying state.
Register the Networkselfmd MCP server in PolicyLayer and add a rule for discover_states: 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.
discover_states is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the discover_states 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 discover_states. 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.
discover_states 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 →