AI agents invoke kinbox_api_raw to trigger actions in Kinbox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool is an explicit escape hatch that allows calling any endpoint of the Kinbox API. Since it can invoke any endpoint, it subsumes all other tools on this server including destructive operations (delete_deal, delete_tag), financial operations (campaigns, deals), write operations, and more.
From the tool's definition 'Faz uma chamada direta para qualquer endpoint da API Kinbox (escape hatch)' — arbitrary API call to any endpoint
Attacks that exploit this kind of access
Faz uma chamada direta para qualquer endpoint da API Kinbox (escape hatch). It is categorised as a Execute tool in the Kinbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kinbox MCP server in PolicyLayer and add a rule for kinbox_api_raw: 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_api_raw is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kinbox_api_raw 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_api_raw. 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_api_raw 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 →