View details of an existing Lemonade insurance policy
AI agents call view_policy to retrieve information from Lemonade 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 policy details without creating, modifying, or deleting data. It is purely informational (Read category). Severity is medium rather than low because policy details may contain sensitive personal and financial information (coverage amounts, premium rates, personal identifiers), making unauthorized access a concern for privacy and potential social engineering, though the tool itself performs no…
From the tool's definition Tool name is 'view_policy' and description states it 'View details of an existing Lemonade insurance policy' — a retrieval operation with no modification.
Attacks that exploit this kind of access
View details of an existing Lemonade insurance policy. It is categorised as a Read tool in the Lemonade MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Lemonade MCP Server MCP server in PolicyLayer and add a rule for view_policy: 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 Lemonade MCP Server. Nothing to install.
view_policy 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 view_policy 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 view_policy. 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.
view_policy is provided by the Lemonade MCP Server MCP server (markswendsen-code/mcp-lemonade). 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 →