AI agents use supabase_insert to create or update resources in VibeServe — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VibeServe environment.
This tool modifies state by inserting data into a persistent database (Supabase). While reversible, it could corrupt application state if an AI agent inserts malformed, duplicate, or sensitive data into the wrong table, affecting production systems. The blast radius depends on table schemas and downstream dependencies, warranting 'medium' severity.
From the tool's definition Tool description states 'Insert a row into a Supabase table' — this creates new data in a database without deleting or overwriting existing records. It is a write operation that is reversible (the inserted row can be deleted).
Attacks that exploit this kind of access
Insert a row into a Supabase table. It is categorised as a Write tool in the VibeServe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VibeServe MCP server in PolicyLayer and add a rule for supabase_insert: 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 VibeServe. Nothing to install.
supabase_insert 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 supabase_insert 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 supabase_insert. 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.
supabase_insert is provided by the VibeServe MCP server (ncsound919/vibeserve). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →