AI agents call wave_list_estimates to retrieve information from Waveapps without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing estimate data with no side effects. It has no ability to create, modify, delete, or execute operations. The blast radius of misuse is minimal—an AI could return business data it shouldn't have access to, but cannot cause financial harm or data destruction. Classified as Read with low severity.
From the tool's definition Tool name 'wave_list_estimates' and description 'Lists estimates' indicate a read operation that retrieves data without modification. GraphQL returns pre-computed buckets (all / active / draft) for filtering, not mutation.
Attacks that exploit this kind of access
Lists estimates for a Wave business. GraphQL returns three buckets at once (all / active / draft) — pick whichever fits. It is categorised as a Read tool in the Waveapps MCP Server, which means it retrieves data without modifying state.
Register the Waveapps MCP server in PolicyLayer and add a rule for wave_list_estimates: 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 Waveapps. Nothing to install.
wave_list_estimates 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 wave_list_estimates 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 wave_list_estimates. 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.
wave_list_estimates is provided by the Waveapps MCP server (lunaparker/waveapps-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 →