Unfollow a pubkey
AI agents use unfollow 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.
Unfollowing modifies the user's social graph by removing a follow relationship. This is a Write operation because it creates/updates data (social connections) reversibly—the action can be undone by following again. It has low severity because it only affects the user's own social preferences with no financial impact, data deletion, or code execution. The blast radius is limited to social graph state changes.
From the tool's definition Tool name 'unfollow' and description 'Unfollow a pubkey' indicate a social graph modification action that creates a new state (unfollowed status) reversibly.
Attacks that exploit this kind of access
Unfollow a pubkey. 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 unfollow: 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.
unfollow 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 unfollow 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 unfollow. 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.
unfollow 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 →