AI agents call get_chain_metrics to retrieve information from Usdd Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries protocol metrics from a data source without creating, modifying, deleting, or executing any operations. It is a pure read operation with no capability to affect system state or perform destructive actions. Low severity due to information-disclosure-only impact.
From the tool's definition Tool name 'get_chain_metrics' and description 'Get chain-level core metrics from website data (mainnet)' indicate data retrieval only. Use of 'Get' verb and 'from website data' clearly show read-only query operation with no side effects.
Attacks that exploit this kind of access
Get chain-level core metrics from website data (mainnet). It is categorised as a Read tool in the Usdd Test MCP Server, which means it retrieves data without modifying state.
Register the Usdd Test MCP server in PolicyLayer and add a rule for get_chain_metrics: 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 Usdd Test. Nothing to install.
get_chain_metrics 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_chain_metrics 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_chain_metrics. 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_chain_metrics is provided by the Usdd Test MCP server (mcp-server-usdd-test). 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 →