AI agents call kinbox_list_deals 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 or queries deal records from the Kinbox CRM without creating, modifying, or deleting data. It is a Read operation. Severity is medium rather than low because deals may contain sensitive business information (customer names, deal values, pipeline stages) that could inform social engineering or competitive intelligence if exposed to an unauthorized agent.
From the tool's definition Tool name 'kinbox_list_deals' and description 'Lista deals (negócios) do CRM Kinbox' indicate retrieval/listing of deal data. The verb 'lista' (list) and absence of modification language confirm read-only operation.
Attacks that exploit this kind of access
Lista deals (negócios) do CRM Kinbox. 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_list_deals: 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_list_deals 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_list_deals 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_list_deals. 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_list_deals 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 →