Get all contacts from Minted address book
AI agents call get_minted_contacts to retrieve information from Minted 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 contact information from an address book without creating, modifying, deleting, or executing any operations. It is purely a query operation with no side effects on data integrity or system state. The blast radius of misuse is limited to exposure of contact information already stored in the user's Minted account.
From the tool's definition Tool name 'get_minted_contacts' and description 'Get all contacts from Minted address book' indicate a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Get all contacts from Minted address book. It is categorised as a Read tool in the Minted MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Minted MCP Server MCP server in PolicyLayer and add a rule for get_minted_contacts: 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 Minted MCP Server. Nothing to install.
get_minted_contacts 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_minted_contacts 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_minted_contacts. 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_minted_contacts is provided by the Minted MCP Server MCP server (markmhendrickson/mcp-server-minted). 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 →