What credentials do I need for NetSuite authentication?

You need 5 values for Token-Based Authentication (TBA): Account ID, Consumer Key, Consumer Secret, Token ID, and Token Secret. All are generated within your NetSuite account under Setup > Integration.

Can I run custom SuiteQL queries?

Yes. The `execute_suiteql` tool executes SQL-like queries against the SuiteQL endpoint. You can query any record type, join tables, and use aggregation functions — all through natural language that the agent translates to SuiteQL.

Does it support NetSuite saved searches?

Absolutely. Use the `run_saved_search` tool with the saved search ID to retrieve its results. This works with any existing saved search in your account — transactions, customers, items, or custom records.

Can I create sales orders through the agent?

Yes. The `create_record` tool with the `salesOrder` record type lets you create full sales orders with line items, pricing, shipping addresses, and payment terms — all through conversation.

Oracle NetSuite MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: Oracle NetSuite
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Oracle NetSuite through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Oracle NetSuite "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Oracle NetSuite?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Oracle NetSuite MCP Server

Connect your Oracle NetSuite account to any AI agent and manage your unified ERP operations through natural conversation.

Pydantic AI validates every Oracle NetSuite tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Financial Management — Query G/L account balances, post journal entries, and retrieve trial balance reports across subsidiaries
Sales Orders — Create and manage sales orders, check fulfillment status, and view invoice history
Purchase Orders — Create POs, track receipt status, and manage vendor bill matching
Inventory & Items — Query item records, stock levels by location, and inventory valuations
Customer Records — Create, read, and update customer master data including contacts and credit limits
Saved Searches — Execute NetSuite saved searches to retrieve complex, pre-filtered datasets
SuiteQL Queries — Run advanced SQL-like queries against any NetSuite record type using SuiteQL

The Oracle NetSuite MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Oracle NetSuite to Pydantic AI via MCP

Follow these steps to integrate the Oracle NetSuite MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from Oracle NetSuite with type-safe schemas

Why Use Pydantic AI with the Oracle NetSuite MCP Server

Pydantic AI provides unique advantages when paired with Oracle NetSuite through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Oracle NetSuite integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Oracle NetSuite connection logic from agent behavior for testable, maintainable code

Oracle NetSuite + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Oracle NetSuite MCP Server delivers measurable value.

Type-safe data pipelines: query Oracle NetSuite with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Oracle NetSuite tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Oracle NetSuite and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Oracle NetSuite responses and write comprehensive agent tests

Oracle NetSuite MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect Oracle NetSuite to Pydantic AI via MCP:

create_record

Provide the record type and a JSON body with field values. Example record types: customer, salesOrder, purchaseOrder, journalEntry. Create a new NetSuite record

delete_record

This action is irreversible. Delete a NetSuite record

execute_suiteql

SuiteQL supports SELECT, JOIN, WHERE, GROUP BY, ORDER BY, and aggregate functions. Example: SELECT id, companyname FROM customer WHERE isinactive = 'F' ORDER BY companyname Execute a SuiteQL query

get_record

Common types: customer, vendor, salesOrder, purchaseOrder, invoice, employee, item, inventoryItem. Get a specific NetSuite record

get_record_metadata

Useful for understanding what fields are available before creating or updating records. Get metadata for a NetSuite record type

list_customers

List NetSuite customers

list_records

Common types: customer, vendor, employee, salesOrder, purchaseOrder, invoice, inventoryItem. List NetSuite records by type

list_sales_orders

List recent sales orders

update_record

Only specify the fields you want to change. Update an existing NetSuite record

Example Prompts for Oracle NetSuite in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Oracle NetSuite immediately.

"Show me the revenue breakdown by subsidiary for March 2026."

"Find all customers with overdue invoices above $10,000."

"Create a sales order for customer 'CUST-1045' with 100 units of item 'SKU-2024-A' at $45 each."

Troubleshooting Oracle NetSuite MCP Server with Pydantic AI

Common issues when connecting Oracle NetSuite to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Oracle NetSuite + Pydantic AI FAQ

Common questions about integrating Oracle NetSuite MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Oracle NetSuite MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.