AI agents invoke execute_query_json to trigger actions in Database. 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 SQL code against live databases. Although it returns results as JSON (suggesting read queries are primary use), SQL execution encompasses Write, Destructive, and Execute operations depending on query content. The Execute category is most appropriate because the tool's core function is query execution with effects determined by the query argument.
From the tool's definition Tool name contains 'execute_query' and description states 'Execute a SQL query'. The tool runs arbitrary SQL queries against multiple database systems (PostgreSQL, Redshift, MySQL, SQL Server, CockroachDB, SQLite).
Documented attack patterns abuse exactly the kind of access execute_query_json gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Database, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_query_json:
{
"version": "1",
"default": "deny",
"tools": {
"execute_query_json": {
"limits": [
{
"counter": "execute_query_json_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_query_json stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a SQL query and return results as JSON. It is categorised as a Execute tool in the Database MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Database MCP server in PolicyLayer and add a rule for execute_query_json: 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 Database. Nothing to install.
execute_query_json 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 execute_query_json 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 execute_query_json. 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.
execute_query_json is provided by the Database MCP server (theralabs/legion-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Database tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Database tools catalogued and risk-classified — across an index of 42,500+ MCP servers.