Show all configured email services as a rich Prefab list card.
AI agents call show_services_card to retrieve information from MiniMail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and displays a list of configured email services. It has no side effects—it does not send emails, modify configurations, execute commands, delete data, or move money. The action is purely informational, retrieving and presenting existing service information in a card format.
From the tool's definition Tool name 'show_services_card' and description 'Show all configured email services as a rich Prefab list card' indicate retrieval and display of existing configuration data with no modification or execution.
Attacks that exploit this kind of access
Show all configured email services as a rich Prefab list card. It is categorised as a Read tool in the MiniMail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MiniMail MCP Server MCP server in PolicyLayer and add a rule for show_services_card: 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 MiniMail MCP Server. Nothing to install.
show_services_card 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 show_services_card 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 show_services_card. 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.
show_services_card is provided by the MiniMail MCP Server MCP server (sandraschi/email-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 →