Sqlsure

Name: Sqlsure
Author: sqlsure

by sqlsurecommunityv0.1.1

sqlsure checks SQL queries against declared schema semantics (such as dbt tests, PK/FK relationships, or introspected catalog metadata) to detect issues like fanout, non-additive measures, unsafe joins, and exposed sensitive columns before execution. It can be used as a library, CI gate, or MCP server that returns machine-actionable fixes for rejected queries.

From the registry: Semantic SQL inspector: catches double-counting, wrong joins, PII exposure before execution.

GitHub Repository Website

Install & configure

Prerequisites

required
Install sqlsure from PyPI
Install the sqlsure Python package so the MCP server module can be run.
```
$ pip install sqlsure
```
https://pypi.org/project/sqlsure/
required
Prepare a semantic model file
Create or obtain a semantic model JSON file and use its absolute path with the MCP server's --model argument.

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `sqlsure` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install sqlsure from PyPI** — Install the sqlsure Python package so the MCP server module can be run. Run: `pip install sqlsure` (https://pypi.org/project/sqlsure/)
- **Prepare a semantic model file** — Create or obtain a semantic model JSON file and use its absolute path with the MCP server's --model argument.

Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","sqlsure.mcp_server","--model","<absolute-path-to-model.json>"]

Note: The README shows the MCP server being launched locally via Python module execution. No environment variables are documented for the MCP server.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: The README shows the MCP server being launched locally via Python module execution. No environment variables are documented for the MCP server.