Execute a Q query on a KDB+ database
AI agents invoke kdb_query to trigger actions in KDB MCP Service. 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.
This tool runs arbitrary Q/KDB+ queries, which can include any operation: reads, writes, deletes, schema changes, or even system-level commands. Since it permits unrestricted query execution, it must be classified at the most severe applicable level. An AI agent could use this to drop tables, delete data, or exfiltrate sensitive financial time-series data.
From the tool's definition 'Execute a Q query on a KDB+ database' — arbitrary Q query execution with no stated restrictions
Attacks that exploit this kind of access
Execute a Q query on a KDB+ database. It is categorised as a Execute tool in the KDB MCP Service MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the KDB MCP Service MCP server in PolicyLayer and add a rule for kdb_query: 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 KDB MCP Service. Nothing to install.
kdb_query 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 kdb_query 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 kdb_query. 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.
kdb_query is provided by the KDB MCP Service MCP server (riteshsonawala/kdb-mcp). 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 →