AI agents use create_project to create or update resources in PostgREST — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PostgREST environment.
This tool creates a new Supabase project, which is a reversible write operation that establishes new cloud infrastructure and associated resources. While significant in scope, it does not irreversibly destroy data (Destructive), move money (Financial), or execute arbitrary code (Execute).
From the tool's definition Tool name is 'create_project' and description states it 'Creates a new Supabase project.' The verb 'creates' indicates data/infrastructure creation, which is a write operation.
Documented attack patterns abuse exactly the kind of access create_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PostgREST, and nothing reaches the server without passing your rules. This is the rule we recommend for create_project:
{
"version": "1",
"default": "deny",
"tools": {
"create_project": {
"limits": [
{
"counter": "create_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_project stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates a new Supabase project. It is categorised as a Write tool in the PostgREST MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PostgREST MCP server in PolicyLayer and add a rule for create_project: 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 PostgREST. Nothing to install.
create_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_project 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 create_project. 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.
create_project is provided by the PostgREST MCP server (supabase/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 32 PostgREST tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
32 PostgREST tools catalogued and risk-classified — across an index of 42,500+ MCP servers.