Run a read-only SELECT and return rows as JSON. Rejects mutations. Optional
AI agents call run_sql_select to retrieve information from Database MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly executes SELECT queries and rejects mutations, making it a read operation. Severity is medium because it still executes arbitrary SQL against a database, which could expose sensitive data if misused, even though writes are blocked.
From the tool's definition "Run a read-only SELECT and return rows as JSON. Rejects mutations."
Attacks that exploit this kind of access
Run a read-only SELECT and return rows as JSON. Rejects mutations. Optional. It is categorised as a Read tool in the Database MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Database MCP Server MCP server in PolicyLayer and add a rule for run_sql_select: 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 MCP Server. Nothing to install.
run_sql_select 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 run_sql_select 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 run_sql_select. 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.
run_sql_select is provided by the Database MCP Server MCP server (vrushil1/database-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 →