create_sql

Generate read-only SQL for a natural language question.

Server Recife Open Data jg-cordeiro/recife-open-data-mcp
Category Write
Risk class Medium
Parameters 00 required

What create_sql does on Recife Open Data

AI agents use create_sql to create or update resources in Recife Open Data — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Recife Open Data environment.

Why create_sql needs a policy

An AI agent can call create_sql faster than any human can review — one bad instruction and it creates or modifies resources in Recife Open Data by the hundred, each call as confident as the last.

Questions about create_sql

What does the create_sql tool do? +

Generate read-only SQL for a natural language question. It is categorised as a Write tool in the Recife Open Data MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_sql? +

Register the Recife Open Data MCP server in PolicyLayer and add a rule for create_sql: 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 Recife Open Data. Nothing to install.

What risk level is create_sql? +

create_sql is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_sql? +

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

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

create_sql is provided by the Recife Open Data MCP server (jg-cordeiro/recife-open-data-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.