AI agents use copy_data to create or update resources in MCP Vertica — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Vertica environment.
The 'copy_data' tool likely performs COPY operations (a common Vertica command for bulk data loading) or similar data insertion/modification actions. This is a Write operation because it creates or modifies data reversibly. Severity is high due to potential for large-scale data modification in a production database.
From the tool's definition Tool name is 'copy_data' on a Vertica database server with SQL query execution and database management capabilities. Description is empty, but the name and server context strongly suggest data copying/insertion operations.
Documented attack patterns abuse exactly the kind of access copy_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Vertica, and nothing reaches the server without passing your rules. This is the rule we recommend for copy_data:
{
"version": "1",
"default": "deny",
"tools": {
"copy_data": {
"limits": [
{
"counter": "copy_data_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}copy_data 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.
copy_data. It is categorised as a Write tool in the MCP Vertica MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Vertica MCP server in PolicyLayer and add a rule for copy_data: 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 MCP Vertica. Nothing to install.
copy_data 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 copy_data 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 copy_data. 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.
copy_data is provided by the MCP Vertica MCP server (nolleh/mcp-vertica). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Vertica, 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.
6 MCP Vertica tools catalogued and risk-classified — across an index of 43,000+ MCP servers.