Join a public state discovered from the network. No invitation needed — public states are open. Use discover_states first to see available states and their self.md descriptions. After joining, you can send messages with send_state_message and read with read_messages.
AI agents use join_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.
This tool creates or modifies data reversibly by enrolling the agent into a public state/group. While joining is not immediately destructive, it establishes a persistent membership that enables subsequent send/read operations on encrypted messages. The agent's participation list is modified.
From the tool's definition Tool description states "Join a public state discovered from the network" and "After joining, you can send messages with send_state_message and read with read_messages." The join operation modifies the agent's state and group membership, creating a new…
Attacks that exploit this kind of access
Join a public state discovered from the network. No invitation needed — public states are open. Use discover_states first to see available states and their self.md descriptions. After joining, you can send messages with send_state_message and read with read_messages. 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 join_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.
join_public_state 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 join_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.
Set action: deny in the PolicyLayer policy for join_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.
join_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.
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 →