execute_postgresql_query

Execute READ-ONLY SQL query on PostgreSQL database using Java connector (SELECT queries ONLY - strict security enforced)

Server MCP Document Converter kittolau/mcp
Category Read
Risk class Low
Parameters 00 required

What execute_postgresql_query does on MCP Document Converter

AI agents call execute_postgresql_query to retrieve information from MCP Document Converter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why execute_postgresql_query needs a policy

The tool claims to enforce read-only SELECT queries only, placing it in the Read category. However, severity is medium because SQL query execution against a database always carries some risk: even SELECT queries can expose sensitive data, and the actual enforcement of read-only restrictions depends on implementation.

From the tool's definition Execute READ-ONLY SQL query on PostgreSQL database using Java connector (SELECT queries ONLY - strict security enforced)

Questions about execute_postgresql_query

What does the execute_postgresql_query tool do? +

Execute READ-ONLY SQL query on PostgreSQL database using Java connector (SELECT queries ONLY - strict security enforced). It is categorised as a Read tool in the MCP Document Converter MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on execute_postgresql_query? +

Register the MCP Document Converter MCP server in PolicyLayer and add a rule for execute_postgresql_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 Document Converter. Nothing to install.

What risk level is execute_postgresql_query? +

execute_postgresql_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit execute_postgresql_query? +

Yes. Add a rate_limit block to the execute_postgresql_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.

How do I block execute_postgresql_query completely? +

Set action: deny in the PolicyLayer policy for execute_postgresql_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.

What MCP server provides execute_postgresql_query? +

execute_postgresql_query is provided by the MCP Document Converter MCP server (kittolau/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.