How to integrate Prisma MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Prisma Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Prisma to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Prisma agent that can create a new postgres database in my project, run a sql query to list all users, delete a database connection by name, get details for a specific prisma project through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Prisma account through Composio's Prisma MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Prisma
  • Configure an AI agent that can use Prisma as a tool
  • Run a live chat session where you can ask the agent to perform Prisma operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Prisma MCP server, and what's possible with it?

The Prisma MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Prisma account. It provides structured and secure access to your database management, so your agent can perform actions like creating projects, managing databases, executing SQL queries, and handling API keys on your behalf.

  • Automated project and database provisioning: Instantly create new Prisma projects and managed PostgreSQL databases in your workspace, complete with connection strings and API keys for fast onboarding.
  • On-demand SQL execution and analysis: Have your agent run SQL commands or select queries for reporting, data inspection, or schema changes—without manual intervention.
  • API key and connection management: Programmatically generate, rotate, or revoke database API keys, ensuring secure and controlled access for all your applications.
  • Workspace and resource monitoring: Retrieve detailed information about your workspaces, projects, and databases, allowing your agent to validate deployments or monitor status in real time.
  • Safe resource cleanup and deletion: Direct your agent to delete databases, projects, or specific connections—helping you maintain a tidy, secure, and cost-effective data platform.

Supported Tools & Triggers

Tools
Create Database ConnectionCreate new api key connection for database access.
Create Project DatabaseCreate new postgres database in an existing prisma project.
Create Prisma ProjectCreate new prisma project with managed postgres database.
Delete Database ConnectionPermanently delete database connection and revoke api key access.
Delete Prisma DatabasePermanently delete prisma database and all stored data.
Delete Prisma ProjectPermanently delete prisma project and all associated resources.
Execute SQL CommandExecute sql commands that modify database data or structure.
Execute SQL QueryExecute sql select queries against prisma databases.
Get Prisma DatabaseRetrieve specific prisma database by id.
Get Prisma ProjectRetrieve specific prisma project by id.
Inspect Database SchemaInspect database schema structure and table information.
List Prisma Accelerate RegionsRetrieve all available regions for prisma accelerate.
List Database BackupsRetrieve list of available backups for a specific database.
List Database ConnectionsRetrieve paginated list of connections for a specific database.
List Project DatabasesRetrieve paginated list of databases for a specific prisma project.
List Prisma Postgres RegionsRetrieve all available regions for prisma postgres.
List Prisma ProjectsRetrieve paginated list of prisma projects accessible to authenticated user.
List Prisma WorkspacesRetrieve paginated list of prisma workspaces accessible to authenticated user.
Restore Database BackupRestore database backup to new database instance.
Transfer Prisma ProjectTransfer prisma project ownership to another user.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Prisma project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Prisma.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Prisma Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["prisma"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only prisma.
  • The router checks the user's Prisma connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Prisma.
  • This approach keeps things lightweight and lets the agent request Prisma tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Prisma. "
        "Help users perform Prisma operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Prisma and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Prisma operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Prisma.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Prisma and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["prisma"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Prisma. "
        "Help users perform Prisma operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Prisma MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Prisma.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Prisma MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Prisma MCP with Claude Agent SDK

Google ADK

Google ADK

Use Prisma MCP with Google ADK

LangChain

LangChain

Use Prisma MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Prisma MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Prisma MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Prisma MCP with LlamaIndex

CrewAI

CrewAI

Use Prisma MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Prisma MCP?

With a standalone Prisma MCP server, the agents and LLMs can only access a fixed set of Prisma tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Prisma and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Prisma tools.

Can I manage the permissions and scopes for Prisma while using Tool Router?

Yes, absolutely. You can configure which Prisma scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Prisma data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free