AI agents call get_cost to retrieve information from PostgREST 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 cost estimate data for informational purposes. While it relates to financial aspects, it does not move money, commit financial obligations, or perform transactions—it merely reads cost information. It falls squarely in the Read category with low severity since the blast radius of misuse is minimal (exposing cost estimates or projections rather than executing payments or deletions).
From the tool's definition Tool name 'get_cost' and description 'Gets the cost of a new project or branch for an organization' indicates a retrieval operation that queries cost information without modifying, executing, or committing financial transactions.
Documented attack patterns abuse exactly the kind of access get_cost 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 get_cost:
{
"version": "1",
"default": "deny",
"tools": {
"get_cost": {}
}
}get_cost is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Gets the cost of a new project or branch for an organization. It is categorised as a Read tool in the PostgREST MCP Server, which means it retrieves data without modifying state.
Register the PostgREST MCP server in PolicyLayer and add a rule for get_cost: 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.
get_cost 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 get_cost 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 get_cost. 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.
get_cost 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.