trackmcp
Back to directory
j4c0bs

mcp-server-sql-analyzer

View on GitHub

MCP server for SQL static analysis.

25 stars PythonServers & Infrastructure Updated Aug 28, 2025

Documentation

mcp-server-sql-analyzer

A Model Context Protocol (MCP) server that provides SQL analysis, linting, and dialect conversion capabilities using SQLGlot.

Overview

The SQL Analyzer MCP server provides tools for analyzing and working with SQL queries. It helps with:

  • SQL syntax validation and linting
  • Converting queries between different SQL dialects (e.g., MySQL to PostgreSQL)
  • Extracting and analyzing table references and dependencies
  • Identifying column usage and relationships
  • Discovering supported SQL dialects

How Claude Uses This Server

As an AI assistant, this server enhances my ability to help users work with SQL efficiently by:

1. Query Validation: I can instantly validate SQL syntax before suggesting it to users, ensuring I provide correct and dialect-appropriate queries.

2. Dialect Conversion: When users need to migrate queries between different database systems, I can accurately convert the syntax while preserving the query's logic.

3. Code Analysis: The table and column reference analysis helps me understand complex queries, making it easier to explain query structure and suggest optimizations.

4. Compatibility Checking: By knowing the supported dialects and their specific features, I can guide users toward database-specific best practices.

This toolset allows me to provide more accurate and helpful SQL-related assistance while reducing the risk of syntax errors or dialect-specific issues.

Tips

Update your personal preferences in Claude Desktop settings to request that generated SQL is first validated using the `lint_sql` tool.

Tools

1. lint_sql

    2. transpile_sql

      3. get_all_table_references

        4. get_all_column_references

          Resources

          SQL Dialect Discovery

          code
          dialects://all

          Returns a list of all supported SQL dialects for use in all tools.

          Configuration

          Add this to your `claude_desktop_config.json`:

          json
          {
            "mcpServers": {
                "sql-analyzer": {
                    "command": "uvx",
                    "args": [
                        "--from",
                        "git+https://github.com/j4c0bs/mcp-server-sql-analyzer.git",
                        "mcp-server-sql-analyzer"
                    ]
                }
            }
          }

          Using uv

          After cloning this repo, add this to your `claude_desktop_config.json`:

          json
          {
            "mcpServers": {
                "sql-analyzer": {
                    "command": "uv",
                    "args": [
                        "--directory",
                        "/path/to/mcp-server-sql-analyzer",
                        "run",
                        "mcp-server-sql-analyzer"
                    ]
                }
            }
          }

          Development

          To run the server in development mode:

          bash
          # Clone the repository
          git clone git@github.com:j4c0bs/mcp-server-sql-analyzer.git
          
          # Run the server
          npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-server-sql-analyzer run mcp-server-sql-analyzer

          To run unit tests:

          bash
          uv run pytest .

          License

          MIT

          Frequently asked questions

          What is mcp-server-sql-analyzer?

          mcp-server-sql-analyzer is MCP server for SQL static analysis.

          How do I install mcp-server-sql-analyzer?

          Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

          Is mcp-server-sql-analyzer open source?

          Yes — it is hosted on GitHub at https://github.com/j4c0bs/mcp-server-sql-analyzer and has 25 stars.

          Related MCP tools

          Run your own MCP server? See who uses it and what to fix.

          Measure it with TrackMCP