Fetches full details of a block using its hash. Returns information such as height, timestamp, transaction count, miner, and size. Can be used to explore block metadata or confirm inclusion of transactions.
AI agents call block_info to retrieve information from Maestro MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
block_info retrieves publicly available blockchain data (block hash, height, timestamp, transaction count, miner, size) without any side effects. It does not create, modify, delete, or execute code. The tool falls squarely into the Read category as it queries and returns immutable historical blockchain information.
From the tool's definition Tool description states it 'Fetches full details of a block' and is used to 'explore block metadata or confirm inclusion of transactions.' The verb 'fetches' and the purpose of exploration indicate data retrieval with no modification, deletion, or execution…
Documented attack patterns abuse exactly the kind of access block_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Maestro MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for block_info:
{
"version": "1",
"default": "deny",
"tools": {
"block_info": {}
}
} block_info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetches full details of a block using its hash. Returns information such as height, timestamp, transaction count, miner, and size. Can be used to explore block metadata or confirm inclusion of transactions. It is categorised as a Read tool in the Maestro MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Maestro MCP Server MCP server in PolicyLayer and add a rule for block_info: 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 Maestro MCP Server. Nothing to install.
block_info 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 block_info 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 block_info. 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.
block_info is provided by the Maestro MCP Server MCP server (maestro-org/maestro-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Maestro MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
117 Maestro MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.