kb_explain

Get the execution plan for a SQL query using EXPLAIN. Use this to analyze query performance, identify full table scans, and optimize queries. Args: - sql (string): The SQL query to explain - analyze (boolean, default false): If true, actually executes the query (EXPLAIN ANALYZE) for real timing d...

Server Kingbase kingbase-mcp-server
Category Read
Risk class Low
Parameters 31 required

What kb_explain does on Kingbase

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

ParameterTypeRequiredDescription
sql string Yes SQL query to explain
format string Output format for the execution plan
analyze boolean Run EXPLAIN ANALYZE (actually executes the query) for real timing data

Parameters from the server's own tool schema.

Why kb_explain needs a policy

EXPLAIN and EXPLAIN ANALYZE are read-only SQL operations that retrieve query execution plans and performance metadata without creating, modifying, or deleting data. Even with the `analyze` flag enabled, the query is executed in a read-only context to gather timing statistics. This is a diagnostic/analytical tool with no side effects, placing it firmly in the Read category.

From the tool's definition Tool description states 'Get the execution plan for a SQL query using EXPLAIN' and 'Use this to analyze query performance, identify full table scans, and optimize queries.' The `analyze` flag notes that when true it 'actually executes the query (EXPLAIN…

Risk signalsAccepts freeform code/query input (sql)

Questions about kb_explain

What does the kb_explain tool do? +

Get the execution plan for a SQL query using EXPLAIN. Use this to analyze query performance, identify full table scans, and optimize queries. Args: - sql (string): The SQL query to explain - analyze (boolean, default false): If true, actually executes the query (EXPLAIN ANALYZE) for real timing data - format ('text' | 'json' | 'yaml'): Output format (default: 'text') Returns: Query execution plan showing scan types, costs, and join strategies. Examples: - sql: "SELECT * FROM users WHERE email = 'test@example.com'" - sql: "SELECT u.*, o.* FROM users u JOIN orders o ON u.id = o.user_id", analyze: true. It is categorised as a Read tool in the Kingbase MCP Server, which means it retrieves data without modifying state.

What parameters does kb_explain accept? +

kb_explain accepts 3 parameters: sql, format, analyze. Required: sql. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on kb_explain? +

Register the Kingbase MCP server in PolicyLayer and add a rule for kb_explain: 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 Kingbase. Nothing to install.

What risk level is kb_explain? +

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

Can I rate-limit kb_explain? +

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

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

kb_explain is provided by the Kingbase MCP server (kingbase-mcp-server). 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.