Execute a read-only SQL query. Only SELECT statements are allowed. Automatically enforces row limits and timeouts.
AI agents call db_query to retrieve information from RunContext without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly restricts execution to SELECT statements and enforces read-only access, placing it firmly in the Read category. Severity is medium rather than low because arbitrary SELECT queries can still expose sensitive data across the entire database schema if an agent is misdirected, even though no writes or destructive actions are possible.
From the tool's definition Execute a read-only SQL query. Only SELECT statements are allowed. Automatically enforces row limits and timeouts.
Attacks that exploit this kind of access
Execute a read-only SQL query. Only SELECT statements are allowed. Automatically enforces row limits and timeouts. It is categorised as a Read tool in the RunContext MCP Server, which means it retrieves data without modifying state.
Register the RunContext MCP server in PolicyLayer and add a rule for db_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 RunContext. Nothing to install.
db_query 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 db_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 db_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.
db_query is provided by the RunContext MCP server (quiet-victory-labs/runcontext). 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 →