Query Clickhouse database (currently unimplemented)
AI agents call search_clickhouse to retrieve information from Datadog Logs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a database query operation, which is fundamentally a read action that retrieves data without modifying it. While Clickhouse queries could theoretically support destructive operations (DROP, DELETE, TRUNCATE), the verb 'Query' and absence of any mention of write/delete capabilities suggest this is intended as a read-only search tool.
From the tool's definition Tool name 'search_clickhouse' and description 'Query Clickhouse database' indicate a read operation. The parenthetical '(currently unimplemented)' suggests the tool is not yet active.
Attacks that exploit this kind of access
Query Clickhouse database (currently unimplemented). It is categorised as a Read tool in the Datadog Logs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Datadog Logs MCP Server MCP server in PolicyLayer and add a rule for search_clickhouse: 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 Datadog Logs MCP Server. Nothing to install.
search_clickhouse 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 search_clickhouse 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 search_clickhouse. 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.
search_clickhouse is provided by the Datadog Logs MCP Server MCP server (rezo8/columbo). 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 →