On-demand health check for any ERC-4626 or Mellow Core vault (no watch required).
AI agents call lido_check_vault to retrieve information from Lido MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health checks are diagnostic read operations that query vault data (ERC-4626 or Mellow Core vault state) to assess operational status. This is a passive information retrieval with no side effects, no transaction execution, and no data modification. The low severity reflects minimal risk if misused—an agent could repeatedly query vaults but cannot cause financial loss or irreversible changes.
From the tool's definition Tool performs an 'on-demand health check' with 'no watch required', indicating it retrieves and queries vault status information without modifying state or executing transactions.
Attacks that exploit this kind of access
On-demand health check for any ERC-4626 or Mellow Core vault (no watch required). It is categorised as a Read tool in the Lido MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Lido MCP Server MCP server in PolicyLayer and add a rule for lido_check_vault: 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 Lido MCP Server. Nothing to install.
lido_check_vault 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 lido_check_vault 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 lido_check_vault. 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.
lido_check_vault is provided by the Lido MCP Server MCP server (the-wunmi/lido-mcp-server). 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 →