Generic request tool to call arbitrary Cube.js REST endpoints.
AI agents invoke raw_request to trigger actions in Cube Js MCP Server. 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 allows calling arbitrary REST endpoints on the Cube.js platform, meaning it can trigger any operation including reads, writes, executes, or destructive actions depending on the endpoint called.
From the tool's definition "Generic request tool to call arbitrary Cube.js REST endpoints"
Documented attack patterns abuse exactly the kind of access raw_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cube Js MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for raw_request:
{
"version": "1",
"default": "deny",
"tools": {
"raw_request": {
"limits": [
{
"counter": "raw_request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}raw_request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generic request tool to call arbitrary Cube.js REST endpoints. It is categorised as a Execute tool in the Cube Js MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cube Js MCP Server MCP server in PolicyLayer and add a rule for raw_request: 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 Cube Js MCP Server. Nothing to install.
raw_request 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 raw_request 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 raw_request. 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.
raw_request is provided by the Cube Js MCP Server MCP server (zsembek/cube.js-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cube Js MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Cube Js MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.