get-latest-block
AI agents call get-latest-block to retrieve information from Lineage MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves blockchain data (the latest block) with no side effects. It is a query operation analogous to other GET/FETCH operations on the server. Reading blockchain state poses minimal risk unless the agent uses the retrieved data to inform harmful actions elsewhere, but the tool itself performs only data retrieval.
From the tool's definition Tool name is 'get-latest-block' and sibling tools include 'get-block-by-number', 'get-transaction-by-hash', 'fetch-balance', and other query operations that are clearly read-only. The server provides blockchain data retrieval operations.
Attacks that exploit this kind of access
get-latest-block. It is categorised as a Read tool in the Lineage MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Lineage MCP Server 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 Lineage MCP Server. 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 Lineage MCP Server MCP server (lineage-foundation/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 →