Analyze, format, validate, lint, parse, and scan SQL through seven MCP tools over Streamable HTTP.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.
Inspect callable tools, capabilities, and parameters exposed to AI agents by GoSQLX.
The ajitpratap0/GoSQLX MCP server makes GoSQLX SQL parsing and analysis functions available to MCP clients. It provides seven tools covering SQL validation, formatting, parsing, linting, security scanning, metadata extraction, and full analysis. These operations are intended for examining SQL text rather than executing queries against a database.
The underlying GoSQLX project is a SQL parsing SDK with AST generation and support for multiple SQL dialects. The README lists PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite, Snowflake, and ClickHouse support. It also describes support for constructs including common table expressions, window functions, MERGE statements, and set operations.
ajitpratap0/GoSQLX MCP server is exposed through Streamable HTTP at https://mcp.gosqlx.dev/mcp. An MCP client connects to that endpoint and invokes the SQL tools with the query text and the relevant operation parameters. Because the endpoint is public and the documented setup does not require credentials, clients can use the remote service without compiling Go code or installing a local binary.
The same project also exists as a Go library, command-line tool, VS Code extension, GitHub Action, and WASM playground. Those are separate access paths; the MCP listing concerns the remote MCP interface.
For a remote connection, configure an MCP client with the endpoint URL. The README gives this Claude command:
No environment variables, API keys, database credentials, or local configuration values are specified for the public MCP endpoint. The README also states that the service can be used from Claude, Cursor, or another MCP client that supports the transport.
If local Go development is preferred, the repository can be obtained with go get github.com/ajitpratap0/GoSQLX, and the CLI can be installed with go install github.com/ajitpratap0/GoSQLX/cmd/gosqlx@latest. Those commands install the library or CLI, not the hosted MCP endpoint.
The seven documented MCP capabilities are:
The broader project describes 30 lint rules, 20 optimizer rules, AST-based formatting, and metadata extraction. These capabilities make ajitpratap0/GoSQLX MCP server relevant for reviewing generated queries, checking SQL before deployment, standardizing formatting, and helping an agent understand tables or other query structure.
This interface is a SQL parser and analyzer, not an ORM or a database connection. The supplied material does not document query execution, schema synchronization, migrations, or connections to a user database. Results depend on the selected SQL dialect and the syntax supported by GoSQLX.
The README presents different performance figures in different sections, including 1.38 million operations per second and a separate listing that cites 1.25 million. Those benchmark figures describe the GoSQLX project generally, not a guaranteed response rate for the hosted MCP endpoint. The project is licensed under Apache-2.0.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/ajitpratap0-gosqlx)<a href="https://allmcps.com/mcp/ajitpratap0-gosqlx"><img src="https://allmcps.com/api/badge/ajitpratap0-gosqlx?style=directory" alt="GoSQLX on AllMCPs" /></a>