Perform select/insert/update/delete against allowed Supabase tables (insert needs jsonOrdered, update/delete need id and version). lifecyclemodels insert/update automatically validate the payload, derive platform json_tg, compute rule_verification, and then write the row; lifecyclemodels select r...
AI agents call Database_CRUD_Tool to permanently remove resources in TianGong-LCA-MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly supports DELETE operations against database tables, which are irreversible and qualify as Destructive. It also performs INSERT and UPDATE (Write), but per the severity hierarchy, Destructive takes precedence. The blast radius is critical because a misused delete could wipe entire lifecycle model records or other allowed tables with no rollback mechanism mentioned.
From the tool's definition 'Perform select/insert/update/delete against allowed Supabase tables' — explicitly includes delete operations; also includes insert and update which are Write-level, but delete is irreversible
Documented attack patterns abuse exactly the kind of access Database_CRUD_Tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TianGong-LCA-MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for Database_CRUD_Tool:
{
"version": "1",
"default": "deny",
"hide": [
"Database_CRUD_Tool"
]
}Database_CRUD_Tool disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Perform select/insert/update/delete against allowed Supabase tables (insert needs jsonOrdered, update/delete need id and version). lifecyclemodels insert/update automatically validate the payload, derive platform json_tg, compute rule_verification, and then write the row; lifecyclemodels select returns id/version/json_ordered only. It is categorised as a Destructive tool in the TianGong-LCA-MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TianGong-LCA-MCP Server MCP server in PolicyLayer and add a rule for Database_CRUD_Tool: 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 TianGong-LCA-MCP Server. Nothing to install.
Database_CRUD_Tool is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the Database_CRUD_Tool 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 Database_CRUD_Tool. 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.
Database_CRUD_Tool is provided by the TianGong-LCA-MCP Server MCP server (linancn/tiangong-lca-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TianGong-LCA-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.
11 TianGong-LCA-MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.