Unsubscribe from a pubsub topic
AI agents use unsubscribe_from_topic to create or update resources in JS-Peer x DeFi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JS-Peer x DeFi MCP Server environment.
Unsubscribing from a pubsub topic modifies the node's subscription state by removing it from a topic channel. This is a reversible action (you can re-subscribe), so it falls under Write rather than Destructive. Misuse could disrupt message delivery or cause an AI agent to miss critical DeFi/cross-chain events, giving it medium severity.
From the tool's definition Unsubscribe from a pubsub topic
Attacks that exploit this kind of access
Unsubscribe from a pubsub topic. It is categorised as a Write tool in the JS-Peer x DeFi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the JS-Peer x DeFi MCP Server MCP server in PolicyLayer and add a rule for unsubscribe_from_topic: 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 JS-Peer x DeFi MCP Server. Nothing to install.
unsubscribe_from_topic 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 unsubscribe_from_topic 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 unsubscribe_from_topic. 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.
unsubscribe_from_topic is provided by the JS-Peer x DeFi MCP Server MCP server (nkovaturient/js-peer-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 →