Toggle between safe and unsafe operation modes for a specific service.
AI agents invoke live_dangerously to trigger actions in Supabase 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 modifies the operational safety controls of the MCP server itself. By switching to 'unsafe' mode, it bypasses built-in safety controls that prevent destructive or dangerous operations across all sibling tools (SQL execution, management API requests, etc.). This is a meta-control that amplifies the blast radius of every other tool on the server, making misuse potentially catastrophic.
From the tool's definition Toggle between safe and unsafe operation modes for a specific service
Documented attack patterns abuse exactly the kind of access live_dangerously gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Supabase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for live_dangerously:
{
"version": "1",
"default": "deny",
"tools": {
"live_dangerously": {
"limits": [
{
"counter": "live_dangerously_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}live_dangerously 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.
Toggle between safe and unsafe operation modes for a specific service. It is categorised as a Execute tool in the Supabase MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Supabase MCP Server MCP server in PolicyLayer and add a rule for live_dangerously: 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 Supabase MCP Server. Nothing to install.
live_dangerously 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 live_dangerously 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 live_dangerously. 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.
live_dangerously is provided by the Supabase MCP Server MCP server (deploya-labs/mcp-supabase). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Supabase 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 Supabase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.