Initialize the agent — starts P2P networking and loads (or generates) identity. Call this first before using any other tools. If the agent is already running, this is a no-op. Returns your fingerprint (your unique ID on the network) and public key.
AI agents invoke agent_init to trigger actions in Networkselfmd. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool starts a P2P networking process and generates or loads cryptographic identity material. It triggers external operations (network initialization, key generation/loading) whose effects depend on state. It is not a simple read — it actively starts a daemon/service.
From the tool's definition "Initialize the agent — starts P2P networking and loads (or generates) identity"
Attacks that exploit this kind of access
Initialize the agent — starts P2P networking and loads (or generates) identity. Call this first before using any other tools. If the agent is already running, this is a no-op. Returns your fingerprint (your unique ID on the network) and public key. It is categorised as a Execute tool in the Networkselfmd MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Networkselfmd MCP server in PolicyLayer and add a rule for agent_init: 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.
agent_init is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the agent_init 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 agent_init. 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.
agent_init 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 →