Get all block heights between two dates
AI agents call getBlockHeights to retrieve information from Somnia 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 historical block height information within a specified date range. It performs no write operations, does not execute code, makes no irreversible changes, and involves no financial transactions. The blast radius of misuse is minimal—an agent could only retrieve blockchain metadata that is already public. This is a standard Read-category operation.
From the tool's definition Tool name 'getBlockHeights' and description 'Get all block heights between two dates' indicate data retrieval with no modification or execution. This is a straightforward query operation on blockchain data.
Attacks that exploit this kind of access
Get all block heights between two dates. It is categorised as a Read tool in the Somnia MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Somnia MCP Server MCP server in PolicyLayer and add a rule for getBlockHeights: 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 Somnia MCP Server. Nothing to install.
getBlockHeights 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 getBlockHeights 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 getBlockHeights. 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.
getBlockHeights is provided by the Somnia MCP Server MCP server (vastavikadi/somnia-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 →