Use this when the user asks for the latest EVM block details from XGRChain.
AI agents call get_latest_block to retrieve information from XGR MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves read-only blockchain data (latest block details). It performs no state changes, does not execute code or transactions, does not delete data, and does not involve financial transactions. It is a simple data retrieval operation typical of blockchain explorers and query APIs.
From the tool's definition Tool name 'get_latest_block' and description 'Use this when the user asks for the latest EVM block details from XGRChain' indicate retrieval of blockchain block data with no modification or side effects.
Attacks that exploit this kind of access
Use this when the user asks for the latest EVM block details from XGRChain. It is categorised as a Read tool in the XGR MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the XGR MCP Gateway MCP server in PolicyLayer and add a rule for get_latest_block: 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 XGR MCP Gateway. Nothing to install.
get_latest_block 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 get_latest_block 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 get_latest_block. 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.
get_latest_block is provided by the XGR MCP Gateway MCP server (xgr-network/xgr-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 →