Query the ntopng Clickhouse database.
AI agents invoke query_ntopng_database to trigger actions in Mcp Ntopng. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While named 'query', executing arbitrary SQL against a ClickHouse database can include destructive or data-exfiltrating statements (SELECT, DROP, DELETE, INSERT, etc.). The description does not restrict to read-only operations, so the most severe applicable category is Execute.
From the tool's definition "Query the ntopng Clickhouse database" — executes arbitrary queries against a ClickHouse database
Attacks that exploit this kind of access
Query the ntopng Clickhouse database. It is categorised as a Execute tool in the Mcp Ntopng MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ntopng MCP server in PolicyLayer and add a rule for query_ntopng_database: 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 Ntopng. Nothing to install.
query_ntopng_database is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query_ntopng_database 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 query_ntopng_database. 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.
query_ntopng_database is provided by the Mcp Ntopng MCP server (marcoeg/mcp-server-ntopng). 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 →