query_read

Run SELECT and other read-only SQL queries on the connected database. This tool only accepts non-destructive queries (SELECT, SHOW, DESCRIBE, EXPLAIN).

Server MCP Universal DB Client izumisy/mcp-universal-db-client
Category Read
Risk class Low
Parameters 00 required

What query_read does on MCP Universal DB Client

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

Why query_read needs a policy

This tool is strictly limited to read-only operations that retrieve or query data without any side effects. The explicit whitelist of allowed query types (SELECT, SHOW, DESCRIBE, EXPLAIN) and prohibition on destructive queries confirms it performs no data modification, deletion, or irreversible actions. Even if an AI misuses this tool, it cannot cause data loss or modification.

From the tool's definition Tool name 'query_read' and description explicitly states 'Run SELECT and other read-only SQL queries' and 'only accepts non-destructive queries (SELECT, SHOW, DESCRIBE, EXPLAIN)'

Questions about query_read

What does the query_read tool do? +

Run SELECT and other read-only SQL queries on the connected database. This tool only accepts non-destructive queries (SELECT, SHOW, DESCRIBE, EXPLAIN). It is categorised as a Read tool in the MCP Universal DB Client MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on query_read? +

Register the MCP Universal DB Client MCP server in PolicyLayer and add a rule for query_read: 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 Universal DB Client. Nothing to install.

What risk level is query_read? +

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

Can I rate-limit query_read? +

Yes. Add a rate_limit block to the query_read 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 query_read completely? +

Set action: deny in the PolicyLayer policy for query_read. 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 query_read? +

query_read is provided by the MCP Universal DB Client MCP server (izumisy/mcp-universal-db-client). 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.