블록 정보를 구독합니다.
AI agents call subscribe_blocks to retrieve information from MCP Mempool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Subscribing to block information is a passive read operation—it monitors and retrieves blockchain data without side effects. No data is created, modified, deleted, or destroyed. No code execution or financial transactions occur. This aligns with the Read category for data retrieval and monitoring operations.
From the tool's definition Tool name 'subscribe_blocks' and description '블록 정보를 구독합니다' (subscribes to block information) indicate subscription to real-time blockchain data feeds. This is a read operation that retrieves block information without modifying data.
Attacks that exploit this kind of access
블록 정보를 구독합니다. It is categorised as a Read tool in the MCP Mempool MCP Server, which means it retrieves data without modifying state.
Register the MCP Mempool MCP server in PolicyLayer and add a rule for subscribe_blocks: 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.
subscribe_blocks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the subscribe_blocks 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 subscribe_blocks. 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.
subscribe_blocks 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 →