Cursor

Cursor is an AI-powered code editor designed to boost productivity by automating repetitive coding tasks. When paired with Prisma, a robust and type-safe toolkit for database workflows, it becomes a powerful solution for managing and optimizing database schemas, queries, and data seeding.

This guide provides detailed instructions for effectively using Prisma with Cursor to:

• Define project-specific best practices with .cursorrules.
• Using Cursor's context-aware capabilities.
• Generate schemas, queries, and seed data tailored to your database.

note

While this guide is focused on Cursor, these patterns should work with any AI editor. Let us know on X if you'd like us to create guides for your preferred tool!

Prisma MCP server

Prisma provides its own Model Context Protocol (MCP) server that lets you manage Prisma Postgres databases, model database schemas and chat through migrations. Learn more about how you can add it to Cursor here. You can also add the Prisma MCP server to Cursor using the one-click installation by clicking on the following link:

This will prompt you to open the Cursor app in your browser. Once opened, you'll be guided to install the Prisma MCP server directly into your Cursor configuration.

Defining project-specific rules with .cursorrules

The .cursorrules file in Cursor allows you to enforce best practices and development standards tailored to your Prisma projects. By defining clear and consistent rules, you can ensure that Cursor generates clean, maintainable, and project-specific code with minimal manual adjustments.

To implement these rules, create a .cursorrules file in the root of your project. Below is an example configuration:

Example .cursorrules file

.cursorrules

You are a senior TypeScript/JavaScript programmer with expertise in Prisma, clean code principles, and modern backend development.
Generate code, corrections, and refactorings that comply with the following guidelines:
TypeScript General Guidelines
Basic Principles
- Use English for all code and documentation.
- Always declare explicit types for variables and functions.
  - Avoid using "any".
  - Create precise, descriptive types.
- Use JSDoc to document public classes and methods.
- Maintain a single export per file.
- Write self-documenting, intention-revealing code.
Nomenclature
- Use PascalCase for classes and interfaces.
- Use camelCase for variables, functions, methods.
- Use kebab-case for file and directory names.
- Use UPPERCASE for environment variables and constants.
- Start function names with a verb.
- Use verb-based names for boolean variables:
  - isLoading, hasError, canDelete
- Use complete words, avoiding unnecessary abbreviations.
  - Exceptions: standard abbreviations like API, URL
  - Accepted short forms: 
    - i, j for loop indices
    - err for errors
    - ctx for contexts
Functions
- Write concise, single-purpose functions.
  - Aim for less than 20 lines of code.
- Name functions descriptively with a verb.
- Minimize function complexity:
  - Use early returns.
  - Extract complex logic to utility functions.
- Leverage functional programming techniques:
  - Prefer map, filter, reduce.
  - Use arrow functions for simple operations.
  - Use named functions for complex logic.
- Use object parameters for multiple arguments.
- Maintain a single level of abstraction.
Data Handling
- Encapsulate data in composite types.
- Prefer immutability.
  - Use readonly for unchanging data.
  - Use as const for literal values.
- Validate data at the boundaries.
Error Handling
- Use specific, descriptive error types.
- Provide context in error messages.
- Use global error handling where appropriate.
- Log errors with sufficient context.
Prisma-Specific Guidelines
Schema Design
- Use meaningful, domain-driven model names.
- Leverage Prisma schema features:
  - Use @id for primary keys.
  - Use @unique for natural unique identifiers.
  - Utilize @relation for explicit relationship definitions.
- Keep schemas normalized and DRY.
- Use meaningful field names and types.
- Implement soft delete with deletedAt timestamp.
- Use Prisma's native type decorators.
Prisma Client Usage
- Always use type-safe Prisma client operations.
- Prefer transactions for complex, multi-step operations.
- Use Prisma middleware for cross-cutting concerns:
  - Logging
  - Soft delete
  - Auditing
- Handle optional relations explicitly.
- Use Prisma's filtering and pagination capabilities.
Database Migrations
- Create migrations for schema changes.
- Use descriptive migration names.
- Review migrations before applying.
- Never modify existing migrations.
- Keep migrations idempotent.
Error Handling with Prisma
- Catch and handle Prisma-specific errors:
  - PrismaClientKnownRequestError
  - PrismaClientUnknownRequestError
  - PrismaClientValidationError
- Provide user-friendly error messages.
- Log detailed error information for debugging.
Testing Prisma Code
- Use in-memory database for unit tests.
- Mock Prisma client for isolated testing.
- Test different scenarios:
  - Successful operations
  - Error cases
  - Edge conditions
- Use factory methods for test data generation.
- Implement integration tests with actual database.
Performance Considerations
- Use select and include judiciously.
- Avoid N+1 query problems.
- Use findMany with take and skip for pagination.
- Leverage Prisma's distinct for unique results.
- Profile and optimize database queries.
Security Best Practices
- Never expose raw Prisma client in APIs.
- Use input validation before database operations.
- Implement row-level security.
- Sanitize and validate all user inputs.
- Use Prisma's built-in protections against SQL injection.
Coding Style
- Keep Prisma-related code in dedicated repositories/modules.
- Separate data access logic from business logic.
- Create repository patterns for complex queries.
- Use dependency injection for Prisma services.
Code Quality
- Follow SOLID principles.
- Prefer composition over inheritance.
- Write clean, readable, and maintainable code.
- Continuously refactor and improve code structure.
Development Workflow
- Use version control (Git).
- Implement comprehensive test coverage.
- Use continuous integration.
- Perform regular code reviews.
- Keep dependencies up to date.

This file ensures consistent and maintainable code generation, reducing manual intervention while improving project quality.

Using Cursor's context-aware capabilities

Cursor's context-aware capabilities let you add specific websites, files, folders or documentation to enhance its understanding of your project. By adding your schema.prisma file as context, you enable Cursor to generate more accurate queries, tests, and seed data based on your database schema.

Add Prisma docs llm.txt file as @Docs context

To improve Cursor's understanding of Prisma-related suggestions in your project, include the /llms.txt markdown file as context. This file offers a concise overview, useful guidance, and links to detailed Prisma documentation—all optimized for LLM processing. Simply navigate to the url and add it as a @Docs resource in your Cursor configuration.

Adding additional Prisma documentation

Cursor already includes built-in context from Prisma documentation, so you don't need to add anything to make us of our docs! You can view the existing resources Cursor uses here.

To stay updated with the latest changes or incorporate additional context, add these resources as @Docs context:

• Prisma Changelog for updates and new features.
• Prisma Blog for practical guides and best practices.

To learn how to add and manage documentation context, visit the Cursor documentation.

Using schema as context

Add your schema.prisma file (or the entire codebase) as context using the @Files syntax before requesting queries, tests, or seed scripts. This allows Cursor to generate precise, schema-driven outputs such as queries, tests, and seed data. For example, in Cursor Chat, you can include your schema by typing @Files followed by adding your schema.prisma file.

Generating Prisma Schema

Cursor can generate Prisma schemas from high-level descriptions, enabling you to quickly establish a solid foundation for your database schema. By providing a clear and detailed prompt, Cursor creates Prisma schemas tailored to your requirements. Whether you need a general foundational schema or a highly specific one for detailed use cases, Cursor can deliver with precision. Here's an example prompt and its corresponding result:

note

If you run the prompts below, you may receive a different outputs because LLMs produce non-deterministic responses.

Prompt to generate Prisma schema

"Create a Prisma schema for a SaaS app using PostgreSQL as a provider with `User`, `Organization`, and `Subscription` models, ensuring all models include `createdAt` and `updatedAt` DateTime fields with defaults, a soft-delete `deletedAt` field, and proper relationships between entities."

Result

schema.prisma

generator client {
  provider = "prisma-client-js"
}

datasource db {
  provider = "postgresql"
  url      = env("DATABASE_URL")
}


model User {
  id            Int           @id @default(autoincrement())
  email         String        @unique
  name          String
  password      String
  createdAt     DateTime      @default(now())
  updatedAt     DateTime      @updatedAt
  deletedAt     DateTime?
  organization  Organization  @relation(fields: [organizationId], references: [id])
  organizationId Int
  role          UserRole     @default(MEMBER)
}


model Organization {
  id            Int           @id @default(autoincrement())
  name          String
  slug          String        @unique
  subscription  Subscription?
  users         User[]
  createdAt     DateTime      @default(now())
  updatedAt     DateTime      @updatedAt
  deletedAt     DateTime?
}

model Subscription {
  id              Int           @id @default(autoincrement())
  organization    Organization  @relation(fields: [organizationId], references: [id])
  organizationId  Int          @unique
  plan           SubscriptionPlan
  status         SubscriptionStatus @default(ACTIVE)
  startDate      DateTime
  endDate        DateTime?
  createdAt      DateTime      @default(now())
  updatedAt      DateTime      @updatedAt
  deletedAt      DateTime?
}

enum UserRole {
  ADMIN
  MEMBER
}

enum SubscriptionPlan {
  FREE
  BASIC
  PREMIUM
  ENTERPRISE
}

enum SubscriptionStatus {
  ACTIVE
  CANCELED
  EXPIRED
  PAST_DUE
}

Generating Prisma queries

Cursor can help you create queries tailored to your Prisma schema, whether for basic data retrieval or complex, optimized operations. To get the best results, focus on writing clear, specific prompts that define your requirements, such as the fields to include, conditions to apply, and relationships to traverse. This ensures Cursor generates accurate, performant, and type-safe queries. Here's an example prompt and its resulting query:

Prompt to generate a database query

"Generate a query to retrieve all User records associated with an Organization that has an `active` Subscription, while excluding any records where the deletedAt field is set."

Result

const activeUsers = await prisma.user.findMany({
  where: {
    deletedAt: null,
    organization: {
      deletedAt: null,
      subscription: {
        deletedAt: null,
        status: 'ACTIVE'
      }
    }
  },
  include: {
    organization: {
      include: {
        subscription: true
      }
    }
  },
  orderBy: {
    createdAt: 'desc'
  },
  skip: 0,
  take: 10
});

Creating seed files with Cursor

Writing seed scripts can be a tedious process, but Cursor simplifies it by quickly generating structured and organized seed code. By providing clear instructions, you can guide Cursor to create scripts that populate your database with realistic data, including handling relationships and complex structures defined in your schema. Here's an example prompt and its resulting seed script:

Prompt to seed the database

"Generate code to populate the Prisma schema with realistic data for the User, Organization, and Subscription models, ensuring all necessary fields are included."

Result

seed.ts

import {
  PrismaClient,
  UserRole,
  SubscriptionPlan,
  SubscriptionStatus,
} from "@prisma/client";

const prisma = new PrismaClient();

async function main() {
  // Clear existing data
  await prisma.user.deleteMany();
  await prisma.subscription.deleteMany();
  await prisma.organization.deleteMany();

  const organizations = [
    {
      name: "Tech Innovators",
      slug: "tech-innovators",
      subscription: {
        plan: SubscriptionPlan.ENTERPRISE,
        status: SubscriptionStatus.ACTIVE,
        startDate: new Date("2024-01-01"),
      },
      users: [
        {
          name: "Emma Thompson",
          email: "emma@techinnovators.com",
          role: UserRole.ADMIN,
          password: "password123",
        },
        {
          name: "Michael Chen",
          email: "michael@techinnovators.com",
          role: UserRole.MEMBER,
          password: "password123",
        },
      ],
    },
    {
      name: "Digital Solutions",
      slug: "digital-solutions",
      subscription: {
        plan: SubscriptionPlan.PREMIUM,
        status: SubscriptionStatus.ACTIVE,
        startDate: new Date("2024-01-15"),
      },
      users: [
        {
          name: "Sarah Wilson",
          email: "sarah@digitalsolutions.com",
          role: UserRole.ADMIN,
          password: "password123",
        },
        {
          name: "James Miller",
          email: "james@digitalsolutions.com",
          role: UserRole.MEMBER,
          password: "password123",
        },
      ],
    },
    {
      name: "Cloud Systems",
      slug: "cloud-systems",
      subscription: {
        plan: SubscriptionPlan.BASIC,
        status: SubscriptionStatus.ACTIVE,
        startDate: new Date("2024-02-01"),
      },
      users: [
        {
          name: "David Garcia",
          email: "david@cloudsystems.com",
          role: UserRole.ADMIN,
          password: "password123",
        },
        {
          name: "Lisa Wang",
          email: "lisa@cloudsystems.com",
          role: UserRole.MEMBER,
          password: "password123",
        },
      ],
    },
    {
      name: "Data Analytics Co",
      slug: "data-analytics",
      subscription: {
        plan: SubscriptionPlan.PREMIUM,
        status: SubscriptionStatus.ACTIVE,
        startDate: new Date("2024-01-10"),
      },
      users: [
        {
          name: "Alex Johnson",
          email: "alex@dataanalytics.com",
          role: UserRole.ADMIN,
          password: "password123",
        },
        {
          name: "Rachel Kim",
          email: "rachel@dataanalytics.com",
          role: UserRole.MEMBER,
          password: "password123",
        },
      ],
    },
    {
      name: "Smart Solutions",
      slug: "smart-solutions",
      subscription: {
        plan: SubscriptionPlan.FREE,
        status: SubscriptionStatus.ACTIVE,
        startDate: new Date("2024-02-15"),
      },
      users: [
        {
          name: "Daniel Brown",
          email: "daniel@smartsolutions.com",
          role: UserRole.ADMIN,
          password: "password123",
        },
        {
          name: "Maria Rodriguez",
          email: "maria@smartsolutions.com",
          role: UserRole.MEMBER,
          password: "password123",
        },
      ],
    },
  ];

  for (const org of organizations) {
    const createdOrg = await prisma.organization.create({
      data: {
        name: org.name,
        slug: org.slug,
        subscription: {
          create: {
            plan: org.subscription.plan,
            status: org.subscription.status,
            startDate: org.subscription.startDate,
          },
        },
      },
    });

    for (const user of org.users) {
      await prisma.user.create({
        data: {
          name: user.name,
          email: user.email,
          password: user.password,
          role: user.role,
          organizationId: createdOrg.id,
        },
      });
    }
  }

  console.log("Seed data created successfully");
}

main()
  .catch((e) => {
    console.error(e);
    process.exit(1);
  })
  .finally(async () => {
    await prisma.$disconnect();
  });

Additional resources

In summary, using Cursor with Prisma simplifies your workflow, from generating schemas and queries to writing seed scripts. By following this guide, you can save time, reduce errors, and focus on building your application.

Learn more about Cursor in their official documentation.

Stay connected with Prisma

Continue your Prisma journey by connecting with our active community. Stay informed, get involved, and collaborate with other developers:

• Follow us on X for announcements, live events and useful tips.
• Join our Discord to ask questions, talk to the community, and get active support through conversations.
• Subscribe on YouTube for tutorials, demos, and streams.
• Engage on GitHub by starring the repository, reporting issues, or contributing to an issue.

We genuinely value your involvement and look forward to having you as part of our community!