How to Use the Erply ERP & POS MCP in Pydantic AI

Q: How do I initialize Erply ERP & POS with Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Create the toolset with MCPToolset("http://...") and pass it to your agent via the toolsets parameter.

Q: Should I use MCPServerHTTP for the Erply ERP & POS connection in Pydantic AI?

No. That class is deprecated. You should use the unified MCPToolset approach for all remote MCP Server connections.

Q: Can Pydantic AI validate the Erply ERP & POS sales documents?

Yes. When the agent calls listsalesdocuments, the framework checks the returning JSON against its internal schema. Bad data throws a validation error immediately.

Enforce strict runtime validation on your Erply ERP & POS data using Pydantic AI to build reliable retail agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Erply ERP & POS MCP to Pydantic AI

Create your Vinkius account to connect Erply ERP & POS to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Erply ERP & POS with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate MCP Server product queries

When your agent searches for items using `search_products_by_name`, you need exact data shapes. Pydantic AI validates the MCP Server response at runtime. If the Erply API returns a string where you expect an integer, the agent fails loudly. You can pull the entire catalog with `list_retail_products`. The framework ensures no silent corruption happens between the API and your application logic. You get exactly what you expect, every single time.

Validate complex pricing structures

Retail pricing logic gets messy fast. The agent calls `list_retail_price_lists` to fetch active promotions. Because Pydantic AI checks the schema, you never have to worry about hallucinated discount fields. For specific items, the agent runs `get_product_detailed_data`. It extracts the exact attributes and settings for that SKU. The agent then processes this data using whichever underlying model you prefer.

Audit stock without hallucinated data

Stockouts cost money. You can instruct the agent to run `list_inventory_stock_levels`. It reads the raw quantities and stops immediately if the data structure changes unexpectedly. To see how those stock levels translate to revenue, the agent triggers `quick_retail_performance_audit`. Setting this MCP setup is straightforward—just pass the endpoint to `MCPToolset` and attach it to your agent.

Setup guide

Set up Erply ERP & POS MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "erply-erp-pos-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Erply ERP & POS tools.",
)

result = await agent.run("List recent Erply ERP & POS transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Erply ERP & POS. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Erply ERP & POS now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Erply ERP & POS MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Create the toolset with `MCPToolset("http://...")` and pass it to your agent via the `toolsets` parameter.

No. That class is deprecated. You should use the unified `MCPToolset` approach for all remote MCP Server connections.

Yes. When the agent calls `list_sales_documents`, the framework checks the returning JSON against its internal schema. Bad data throws a validation error immediately.

It does. Pydantic AI is model-agnostic. You can route the MCP server data through OpenAI, Anthropic, or a local model running on your own hardware.

The server accesses raw sales invoices and transaction logs. Vinkius handles the authentication with ephemeral tokens, ensuring your API credentials are never exposed or saved to disk.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript