클라이언트의 모든 구독을 해제합니다.
AI agents use unsubscribe_client to create or update resources in MCP Mempool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Mempool environment.
This tool cancels/removes active subscriptions for a client, which is a reversible modification of subscription state (subscriptions can be re-established). It does not delete data, execute code, or involve financial transactions. It modifies a client's subscription configuration, fitting the Write category. Severity is low as misuse would only stop data feeds, not cause data loss or financial harm.
From the tool's definition '클라이언트의 모든 구독을 해제합니다' translates to 'Unsubscribes all subscriptions of a client'
Attacks that exploit this kind of access
클라이언트의 모든 구독을 해제합니다. It is categorised as a Write tool in the MCP Mempool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Mempool MCP server in PolicyLayer and add a rule for unsubscribe_client: 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 MCP Mempool. Nothing to install.
unsubscribe_client 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_client 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_client. 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_client is provided by the MCP Mempool MCP server (jaducku/mcp-mempool). 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 →