mcpbeat Sign in

SQL Preview MCP Server

by fadnavismehul Your server? Claim it
local only

SQL Preview runs on your own machine — the client starts it, so there is no endpoint to ping. 80 installs a week from npm.

Run governed SQL queries and inspect database schemas from MCP agents.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 178 · avg 53 · -78% w/w
a month agotoday
80
Installs / week
npm · sql-preview
Stars
on GitHub
Last commit
0 releases in 90 days
License
language unknown

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add sql-preview -- npx -y sql-preview
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "sql-preview": {
      "args": [
        "-y",
        "sql-preview"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.sql-preview]
command = "npx"
args = ["-y", "sql-preview"]
.cursor/mcp.json
{
  "mcpServers": {
    "sql-preview": {
      "args": [
        "-y",
        "sql-preview"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "sql-preview": {
      "args": [
        "-y",
        "sql-preview"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: SQL_PREVIEW_CONNECTIONS (JSON array of SQL Preview connection profiles for headless use.), SQL_PREVIEW_MCP_SAFE_MODE (Set to false to allow mutating SQL. Defaults to true.), SQL_PREVIEW_MAX_ROWS (Maximum rows returned by query tools. Defaults to 10000.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to SQL Preview

same job, measured the same way
Grain
by pattrnlabs

Run SQL queries and inspect database schemas through safe, visible MCP tools.

191 installs/wk local only
Postgres
by ofershap

PostgreSQL MCP — query databases, inspect schemas, explain queries.

34 installs/wk local only
Sqlite
by ofershap

SQLite MCP — query databases, inspect schemas, explain queries, export data.

139 installs/wk local only
AdoMcp
by john0king

Database MCP server for schema discovery, comments, and SQL queries.

local only
LINQ to DB
by linq2db

Inspect database schemas and execute SQL queries across multiple database providers with LINQ to DB.

local only
MySQL MCP
by gistrec

MCP server for one MySQL database: schema, read-only queries and guarded writes.

27 installs/wk local only
Database Admin
by cybeleri

Database admin MCP: schema inspection, query optimization for PostgreSQL and MySQL

26 installs/wk local only
MySQL MCP Server
by musaddiq-dev

Python MCP server for MySQL database inspection and querying

79 installs/wk local only

SQL Preview — questions

Answers built from our own checks of this server.

Why is there no uptime for SQL Preview?
SQL Preview runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package sql-preview was installed 80 times last week.
Is SQL Preview still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect SQL Preview?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls sql-preview straight from npm; nothing to host, nothing to sign up for.
How many people use SQL Preview?
The npm package sql-preview was installed 80 times in the last week. Week over week that is -78%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.