Skip to main content

MCP Server

The Model-Context-Protocol (MCP) gives LLMs a way to call APIs and thus access external systems in a well-defined manner. Prisma's MCP server gives LLMs the ability to manage Prisma Postgres databases (e.g. spin up new database instances or run schema migrations).

note

The Prisma MCP server is available via the Prisma CLI command prisma platform mcp --early-access and is currently available in Early Access. See below for how to integrate it in your favorite AI tool. It uses the stdio transport mechanism.

Usage​

The Prisma MCP server follows the standard JSON-based configuration for MCP servers. Here's what it looks like:

{
  "mcpServers": {
    "Prisma": {
      "command": "npx",
      "args": ["-y", "prisma", "mcp"]
    }
  }
}

Sample prompts​

Here are some sample prompts you can use when the MCP server is running:

  • Log me into the Prisma Console.
  • Create a database in the US region.
  • Create a new Product table in my database.

Integrating in AI tools​

AI tools have different ways of integrating MCP servers. In most cases, there are dedicated configuration files in which you add the JSON configuration from above. The configuration contains a command for starting the server that'll be executed by the respective tool so that the server is available to its LLM.

In this section, we're covering the config formats of the most popular AI tools.

Cursor​

To learn more about Cursor's MCP integration, check out the Cursor MCP docs.

Add via Cursor Settings UI​

When opening the Cursor Settings, you can add the Prisma MCP Server as follows:

  1. Select MCP in the settings sidenav
  2. Click + Add new global MCP server
  3. Add the Prisma snippet to the mcpServers JSON object: 
    {
      "mcpServers": {
        "Prisma": {
          "command": "npx",
          "args": ["-y", "prisma", "mcp"]
        }
      }
    }

Global configuration​

Adding it via the Cursor Settings settings will modify the global ~/.cursor/mcp.json config file. In this case, the Prisma MCP server will be available in all your Cursor projects:

~/.cursor/mcp.json
{
  "mcpServers": {
    "Prisma": {
      "command": "npx",
      "args": ["-y", "prisma", "mcp"]
    },
    // other MCP servers
  }
}

Project configuration​

If you want the Prisma MCP server to be available only in specific Cursor projects, add it to the Cursor config of the respective project inside the .cursor directory in the project's root:

.cursor/mcp.json
{
  "mcpServers": {
    "Prisma": {
      "command": "npx",
      "args": ["-y", "prisma", "mcp"]
    },
    // other MCP servers
  }
}

Windsurf​

To learn more about Windsurf's MCP integration, check out the Windsurf MCP docs.

Add via Windsurf Settings UI​

When opening the Windsurf Settings (via Windsurf - Settings > Advanced Settings or Command Palette > Open Windsurf Settings Page), you can add the Prisma MCP Server as follows:

  1. Select Cascade in the settings sidenav
  2. Click Add Server
  3. Add the Prisma snippet to the mcpServers JSON object: 
    {
      "mcpServers": {
        "Prisma": {
          "command": "npx",
          "args": ["-y", "prisma", "mcp"]
        }
      }
    }

Global configuration​

Adding it via the Windsurf Settings will modify the global ~/.codeium/windsurf/mcp_config.json config file. Alternatively, you can also manually add it to that file:

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "Prisma": {
      "command": "npx",
      "args": ["-y", "prisma", "mcp"]
    },
    // other MCP servers
  }
}

Claude Code​

Claude Code is a terminal-based AI tool where you can add MCP server using the claud mcp add command:

claude mcp add prisma npx prisma mcp

Learn more in the Claude Code MCP docs.

Claude Desktop​

Follow the instructions in the Claude Desktop MCP docs to create the required configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Then add the JSON snippet to that configuration file:

{
  "mcpServers": {
    "Prisma": {
      "command": "npx",
      "args": ["-y", "prisma", "mcp"]
    },
    // other MCP servers
  }
}

OpenAI Agents SDK​

Here's an example for using the Prisma MCP server in a Python script via the OpenAI Agents SDK:

from openai import AsyncOpenAI
from openai.types.beta import Assistant
from openai.beta import AsyncAssistantExecutor
from openai.experimental.mcp import MCPServerStdio
from openai.types.beta.threads import Message, Thread
from openai.types.beta.tools import ToolCall

# Async context required for MCPServerStdio
import asyncio

async def main():
    # Start the Prisma MCP server using stdio
    async with MCPServerStdio(
        params={
            "command": "npx",
            "args": ["-y", "prisma", "mcp"]
        }
    ) as prisma_server:
        # Optional: view available tools
        tools = await prisma_server.list_tools()
        print("Available tools:", [tool.name for tool in tools])

        # Set up the agent with MCP server
        agent = Assistant(
            name="Prisma Assistant",
            instructions="Use the Prisma tools to help the user with database tasks.",
            mcp_servers=[prisma_server],
        )

        executor = AsyncAssistantExecutor(agent=agent)

        # Create a thread and send a message
        thread = Thread(messages=[Message(role="user", content="Create a new user in the database")])
        response = await executor.run(thread=thread)

        print("Agent response:")
        for message in response.thread.messages:
            print(f"{message.role}: {message.content}")

# Run the async main function
asyncio.run(main())