Current mempool size + tx count + total fees.
AI agents call mempool_stats to retrieve information from Mcp Mempool Space without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns read-only blockchain statistics (mempool size, transaction count, fee information). It retrieves existing data without creating, modifying, deleting, or executing any operations. The tool has no side effects and poses minimal risk even if misused by an AI agent, as it only returns publicly available mempool information.
From the tool's definition Tool name 'mempool_stats' and description 'Current mempool size + tx count + total fees' indicates retrieval of aggregate mempool statistics with no parameters that modify data.
Attacks that exploit this kind of access
Current mempool size + tx count + total fees. It is categorised as a Read tool in the Mcp Mempool Space MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mempool Space MCP server in PolicyLayer and add a rule for mempool_stats: 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 Space. Nothing to install.
mempool_stats 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 mempool_stats 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 mempool_stats. 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.
mempool_stats is provided by the Mcp Mempool Space MCP server (pipeworx-io/mcp-mempool-space). 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 →