Returns information about the most recent blocks
AI agents call get-latest-blocks to retrieve information from Osmosis 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 blockchain data without modifying state, executing code, or affecting financial assets. It is a straightforward read operation with minimal risk if misused by an AI agent, as it cannot alter blockchain state or cause harm beyond potential information disclosure (low severity).
From the tool's definition Tool name 'get-latest-blocks' and description 'Returns information about the most recent blocks' indicate a data retrieval operation with no side effects. This is a query operation that retrieves blockchain block data.
Attacks that exploit this kind of access
Returns information about the most recent blocks. It is categorised as a Read tool in the Osmosis MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Osmosis MCP Server MCP server in PolicyLayer and add a rule for get-latest-blocks: 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 Osmosis MCP Server. Nothing to install.
get-latest-blocks 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-blocks 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-blocks. 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-blocks is provided by the Osmosis MCP Server MCP server (myronkoch-dev/mcp-osmosis). 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 →