Execute a raw SQL query against the database with optional parameter values
AI agents invoke query to trigger actions in Mcp Sqlite. 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 executes arbitrary raw SQL, which can include SELECT, INSERT, UPDATE, DELETE, DROP, or any other SQL statement. Because it permits unrestricted DDL and DML (including destructive operations like DROP TABLE or DELETE without WHERE), it spans Read through Destructive. Per the rules, the most severe applicable category is chosen.
From the tool's definition "Execute a raw SQL query against the database with optional parameter values" — arbitrary raw SQL execution
Attacks that exploit this kind of access
Execute a raw SQL query against the database with optional parameter values. It is categorised as a Execute tool in the Mcp Sqlite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Sqlite MCP server in PolicyLayer and add a rule for 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 Mcp Sqlite. Nothing to install.
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 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 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.
query is provided by the Mcp Sqlite MCP server (mcp-sqlite). 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 →