Publish a signed event to relays
AI agents use publishNostrEvent to create or update resources in Nostr Tools for AI Agents — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nostr Tools for AI Agents environment.
Publishing a signed event to Nostr relays creates/broadcasts new content on the network. This is a write operation — it sends data to external relays. While it has side effects (the event becomes publicly visible on the network), it is not inherently destructive or financial. Severity is medium because a misused agent could spam or post unwanted content publicly on behalf of a user's identity.
From the tool's definition Publish a signed event to relays
Attacks that exploit this kind of access
Publish a signed event to relays. It is categorised as a Write tool in the Nostr Tools for AI Agents MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nostr Tools for AI Agents MCP server in PolicyLayer and add a rule for publishNostrEvent: 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 Nostr Tools for AI Agents. Nothing to install.
publishNostrEvent 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 publishNostrEvent 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 publishNostrEvent. 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.
publishNostrEvent is provided by the Nostr Tools for AI Agents MCP server (jorgenclaw/nostr-mcp-server). 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 →