Overview

The MCP Neon Server bridges AI and serverless databases by letting language models (LLMs) work directly with Neon's serverless PostgreSQL platform. Neon provides instant database provisioning, automatic scaling, and database branching capabilities that make it ideal for modern development workflows.

Created by:

Developed by Neon

Key Features

⚡

Serverless PostgreSQL

Instant provisioning with automatic scaling and zero operational overhead

🌿

Database Branching

Create instant database branches for development, testing, and migrations

🔄

Project Management

Manage projects, branches, and compute resources programmatically

🎯

Advanced Operations

Schema migrations, query tuning, and performance optimization workflows

Available Tools

Quick Reference

Tool	Purpose	Category
`list_projects`	List all Neon projects	Project Mgmt
`create_project`	Create new project	Project Mgmt
`describe_project`	Get project details	Project Mgmt
`delete_project`	Remove project	Project Mgmt
`create_branch`	Create database branch	Branch Mgmt
`delete_branch`	Remove branch	Branch Mgmt
`describe_branch`	Get branch details	Branch Mgmt
`list_branch_computes`	List compute endpoints	Branch Mgmt
`run_sql`	Execute SQL query	Query
`run_sql_transaction`	Execute transaction	Query
`get_database_tables`	List tables	Schema
`describe_table_schema`	Get table structure	Schema
`get_connection_string`	Get connection URL	Connection
`list_slow_queries`	Analyze performance	Performance
`explain_sql_statement`	Query execution plan	Performance
`prepare_database_migration`	Start migration workflow	Migration
`complete_database_migration`	Finish migration	Migration
`prepare_query_tuning`	Start query optimization	Performance
`complete_query_tuning`	Apply optimizations	Performance
`provision_neon_auth`	Setup Neon Auth	Auth

Detailed Usage

list_projects▶

Retrieve a list of your Neon projects with summary information.

use_mcp_tool({
  server_name: "neon",
  tool_name: "list_projects",
  arguments: {
    limit: 10  // Optional: default 10
  }
});

Returns project IDs, names, regions, and creation timestamps.

create_project▶

Create a new Neon project with custom configuration.

use_mcp_tool({
  server_name: "neon",
  tool_name: "create_project",
  arguments: {
    name: "production-db",
    region_id: "aws-us-east-2"
  }
});

Creates project with default database and compute endpoint.

create_branch▶

Create a new database branch for development or testing.

use_mcp_tool({
  server_name: "neon",
  tool_name: "create_branch",
  arguments: {
    project_id: "project-id-123",
    parent_branch: "main",
    name: "feature-new-schema"
  }
});

Instantly creates a copy-on-write branch from parent.

run_sql▶

Execute SQL queries with optional parameterization.

use_mcp_tool({
  server_name: "neon",
  tool_name: "run_sql",
  arguments: {
    project_id: "project-id-123",
    branch_id: "branch-id-456",
    database: "neondb",
    sql: "SELECT * FROM users WHERE id = $1",
    params: [42]
  }
});

Supports both read and write operations with parameters.

run_sql_transaction▶

Execute multiple SQL statements as an atomic transaction.

use_mcp_tool({
  server_name: "neon",
  tool_name: "run_sql_transaction",
  arguments: {
    project_id: "project-id-123",
    branch_id: "branch-id-456",
    database: "neondb",
    queries: [
      "INSERT INTO accounts (name, balance) VALUES ('Alice', 1000)",
      "INSERT INTO accounts (name, balance) VALUES ('Bob', 500)",
      "UPDATE stats SET total_accounts = total_accounts + 2"
    ]
  }
});

All queries succeed or fail together.

get_database_tables▶

List all tables in a database with optional schema filtering.

// List all tables in public schema
use_mcp_tool({
  server_name: "neon",
  tool_name: "get_database_tables",
  arguments: {
    project_id: "project-id-123",
    branch_id: "branch-id-456",
    database: "neondb",
    schema: "public"  // Optional, defaults to 'public'
  }
});

Returns table names and metadata.

describe_table_schema▶

Get detailed schema information for a specific table.

use_mcp_tool({
  server_name: "neon",
  tool_name: "describe_table_schema",
  arguments: {
    project_id: "project-id-123",
    branch_id: "branch-id-456",
    database: "neondb",
    table: "users",
    schema: "public"
  }
});

Returns columns, data types, constraints, and indexes.

prepare_database_migration▶

Initiate a safe migration workflow using database branching.

use_mcp_tool({
  server_name: "neon",
  tool_name: "prepare_database_migration",
  arguments: {
    project_id: "project-id-123",
    branch_id: "main",
    migration_sql: "ALTER TABLE users ADD COLUMN email_verified BOOLEAN DEFAULT false"
  }
});

Creates temporary branch and tests migration safely.

list_slow_queries▶

Identify performance bottlenecks by analyzing slow queries.

use_mcp_tool({
  server_name: "neon",
  tool_name: "list_slow_queries",
  arguments: {
    project_id: "project-id-123",
    branch_id: "branch-id-456",
    database: "neondb",
    min_duration_ms: 1000,  // Queries slower than 1s
    limit: 10
  }
});

Requires pg_stat_statements extension enabled.

explain_sql_statement▶

Analyze query execution plans for optimization.

use_mcp_tool({
  server_name: "neon",
  tool_name: "explain_sql_statement",
  arguments: {
    project_id: "project-id-123",
    branch_id: "branch-id-456",
    database: "neondb",
    sql: "SELECT * FROM orders WHERE user_id = 123 AND created_at > NOW() - INTERVAL '30 days'"
  }
});

Returns detailed execution plan with cost estimates.

provision_neon_auth▶

Setup Neon Auth integration with Stack Auth.

use_mcp_tool({
  server_name: "neon",
  tool_name: "provision_neon_auth",
  arguments: {
    project_id: "project-id-123"
  }
});

Configures authentication infrastructure automatically.

Installation

{
  "mcpServers": {
    "neon": {
      "command": "npx",
      "args": [
        "-y",
        "@neondatabase/mcp-server-neon",
        "start",
        "<YOUR_NEON_API_KEY>"
      ]
    }
  }
}

API Key Required:

You need to create a Neon API key from the Neon Console under Account Settings → API Keys.

Setup Guide

1. Create Neon Account

Sign up at Neon Console
Create your first project (or use existing one)
Note your project ID from the project dashboard

2. Generate API Key

Go to Account Settings → API Keys
Click "Create API Key"
Give it a descriptive name (e.g., "MCP Integration")
Copy the API key immediately (shown only once)
Store it securely

3. Configure MCP Server

Add the API key to your MCP configuration as shown in the Installation section above.

Project Selection:

The server can work with multiple projects. Specify the project_id in each tool call to target different projects.

Common Use Cases

1. Development Branch Workflow

Create isolated database branches for feature development:

// Create feature branch
use_mcp_tool({
  server_name: "neon",
  tool_name: "create_branch",
  arguments: {
    project_id: "my-project",
    parent_branch: "main",
    name: "feature-user-profiles"
  }
});

// Run migrations on feature branch
use_mcp_tool({
  server_name: "neon",
  tool_name: "run_sql",
  arguments: {
    project_id: "my-project",
    branch_id: "feature-user-profiles",
    database: "neondb",
    sql: `
      CREATE TABLE user_profiles (
        id SERIAL PRIMARY KEY,
        user_id INTEGER REFERENCES users(id),
        bio TEXT,
        avatar_url TEXT,
        created_at TIMESTAMPTZ DEFAULT NOW()
      )
    `
  }
});

// Test the changes, then delete branch when done
use_mcp_tool({
  server_name: "neon",
  tool_name: "delete_branch",
  arguments: {
    project_id: "my-project",
    branch_id: "feature-user-profiles"
  }
});

2. Safe Schema Migrations

Use the migration workflow for production changes:

// Prepare migration (creates test branch)
use_mcp_tool({
  server_name: "neon",
  tool_name: "prepare_database_migration",
  arguments: {
    project_id: "my-project",
    branch_id: "main",
    migration_sql: `
      ALTER TABLE orders
      ADD COLUMN tracking_number VARCHAR(100),
      ADD COLUMN shipped_at TIMESTAMPTZ
    `
  }
});

// Test migration on temporary branch...
// If successful, complete the migration

use_mcp_tool({
  server_name: "neon",
  tool_name: "complete_database_migration",
  arguments: {
    project_id: "my-project",
    migration_id: "migration-xyz"
  }
});

3. Query Performance Analysis

Identify and optimize slow queries:

// Find slow queries
use_mcp_tool({
  server_name: "neon",
  tool_name: "list_slow_queries",
  arguments: {
    project_id: "my-project",
    branch_id: "main",
    database: "neondb",
    min_duration_ms: 500,
    limit: 10
  }
});

// Analyze specific query
use_mcp_tool({
  server_name: "neon",
  tool_name: "explain_sql_statement",
  arguments: {
    project_id: "my-project",
    branch_id: "main",
    database: "neondb",
    sql: "SELECT * FROM orders WHERE status = 'pending' ORDER BY created_at DESC"
  }
});

// Optimize using query tuning workflow
use_mcp_tool({
  server_name: "neon",
  tool_name: "prepare_query_tuning",
  arguments: {
    project_id: "my-project",
    branch_id: "main",
    query: "SELECT * FROM orders WHERE status = 'pending' ORDER BY created_at DESC"
  }
});

4. Multi-Environment Management

Manage development, staging, and production databases:

// List all projects
use_mcp_tool({
  server_name: "neon",
  tool_name: "list_projects",
  arguments: { limit: 20 }
});

// Get details for production project
use_mcp_tool({
  server_name: "neon",
  tool_name: "describe_project",
  arguments: {
    project_id: "prod-project-id"
  }
});

// List compute endpoints for scaling info
use_mcp_tool({
  server_name: "neon",
  tool_name: "list_branch_computes",
  arguments: {
    project_id: "prod-project-id",
    branch_id: "main"
  }
});

5. Database Inspection and Schema Discovery

Explore database structure programmatically:

// List all tables
use_mcp_tool({
  server_name: "neon",
  tool_name: "get_database_tables",
  arguments: {
    project_id: "my-project",
    branch_id: "main",
    database: "neondb",
    schema: "public"
  }
});

// Get detailed schema for specific table
use_mcp_tool({
  server_name: "neon",
  tool_name: "describe_table_schema",
  arguments: {
    project_id: "my-project",
    branch_id: "main",
    database: "neondb",
    table: "users",
    schema: "public"
  }
});

Neon-Specific Features

Database Branching

Neon's branching is a game-changer for database workflows:

Instant copies: Create database branches in seconds using copy-on-write
Cost-effective: Only changed data consumes additional storage
Safe testing: Test migrations and schema changes without affecting production
CI/CD integration: Create ephemeral databases for each pull request

Autoscaling

Neon automatically scales compute resources:

Scale to zero: Compute automatically suspends during inactivity
Auto-resume: Instantly resumes when queries arrive
Cost optimization: Pay only for actual usage, not idle time

Connection Pooling

Built-in connection pooling for better performance:

Managed connection pool included
Reduces connection overhead
Better resource utilization

Best Practices

Use branches for development: Never test schema changes on production branches
Enable pg_stat_statements: Required for query performance analysis
Monitor slow queries: Regularly check for performance bottlenecks
Use transactions: Ensure data consistency with run_sql_transaction
Leverage autoscaling: Design apps to handle compute suspension gracefully
Clean up branches: Delete unused branches to optimize storage costs

Sources

Datadog MCP Server

Datadog MCP servers enable AI models to interact with Datadog observability: metrics, logs, traces, monitors, dashboards, incidents, and infrastructure insights.

YouTube Research MCP Server

YouTube Research MCP servers enable AI models to interact with YouTube content, providing capabilities for video information retrieval, transcript management, channel analysis, and playlist management.

Sentry MCP Server

Sentry MCP servers enable AI models to interact with Sentry's error monitoring and performance tracking platform, providing capabilities for analyzing errors, tracking performance, and assisting in debugging applications.

Neon MCP Server

Overview

Key Features

Serverless PostgreSQL

Database Branching

Project Management

Advanced Operations

Available Tools

Quick Reference

Detailed Usage

Installation

Setup Guide

1. Create Neon Account

2. Generate API Key

3. Configure MCP Server

Common Use Cases

1. Development Branch Workflow

2. Safe Schema Migrations

3. Query Performance Analysis

4. Multi-Environment Management

5. Database Inspection and Schema Discovery

Neon-Specific Features

Database Branching

Autoscaling

Connection Pooling

Best Practices

Sources

Related Articles

Datadog MCP Server

YouTube Research MCP Server

Sentry MCP Server

On this page