AI agents call kinbox_get_contact to retrieve information from Kinbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries a single contact record by identifier. It has no side effects, does not modify, delete, or execute operations. It falls squarely into the Read category with low severity since contact data retrieval poses minimal risk unless the contacts contain highly sensitive personal information, but the tool itself performs only a lookup.
From the tool's definition Tool description states 'Busca um contato pelo ID' (searches for a contact by ID) - a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Busca um contato pelo ID. It is categorised as a Read tool in the Kinbox MCP Server, which means it retrieves data without modifying state.
Register the Kinbox MCP server in PolicyLayer and add a rule for kinbox_get_contact: 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 Kinbox. Nothing to install.
kinbox_get_contact 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 kinbox_get_contact 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 kinbox_get_contact. 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.
kinbox_get_contact is provided by the Kinbox MCP server (vergamini65-boop/kinbox-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 →