Execute a read-only SQL query (SELECT or WITH statements only).
AI agents call execute_read_only_query to retrieve information from NLP 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 is explicitly restricted to SELECT and WITH statements, making it read-only with no data modification capability. However, severity is medium because even read-only SQL access can expose sensitive data at scale if an AI agent crafts broad or unintended queries — the blast radius is data exfiltration, not data modification.
From the tool's definition Execute a read-only SQL query (SELECT or WITH statements only)
Attacks that exploit this kind of access
Execute a read-only SQL query (SELECT or WITH statements only). It is categorised as a Read tool in the NLP Database MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NLP Database MCP Server MCP server in PolicyLayer and add a rule for execute_read_only_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 NLP Database MCP Server. Nothing to install.
execute_read_only_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 execute_read_only_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 execute_read_only_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.
execute_read_only_query is provided by the NLP Database MCP Server MCP server (lisito11/nlp-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 →