Manage Neon serverless Postgres databases with natural language
The Neon Postgres MCP Server lets your AI assistant manage Neon's serverless Postgres databases with natural language. Create and manage branches, run SQL queries, handle migrations, and monitor database performance.
Built by Neon, this server leverages Neon's unique branching capability that lets you create instant database copies for testing and development. It supports full database management including creating projects, branches, and running queries.
Ideal for developers using Neon's serverless Postgres platform who want AI-assisted database management, schema design, and data exploration with the added power of instant branching.
Valid MCP server (1 strong, 1 medium validity signals). 11 known CVEs in dependencies (0 critical, 5 high severity) Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.
3 files analyzed · 12 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Unverified package source
We couldn't verify that the installable package matches the reviewed source code. Proceed with caution.
Set these up before or after installing:
Environment variable: SERVER_HOST
Environment variable: UPSTREAM_OAUTH_HOST
Environment variable: CLIENT_ID
Environment variable: CLIENT_SECRET
Environment variable: COOKIE_SECRET
Environment variable: KV_URL
Environment variable: OAUTH_DATABASE_URL
Environment variable: LOG_LEVEL
Add this to your MCP configuration file:
{
"mcpServers": {
"neon-postgres": {
"args": [
"-y",
"@neondatabase/mcp-server-neon"
],
"command": "npx"
}
}
}Be the first to review this server!
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption