How do I find my Holded API Key?

Log in to your Holded account, click on the **Settings** icon (top right), go to **Developers**, and you will find your unique **API Key** listed there. You can create multiple keys for different integrations.

What document types are supported in the invoicing tools?

This integration currently focuses on the `invoice` document type. For other types like sales orders or purchase orders, you can use the generic `list_invoices` logic if they are mapped under the same module in your instance.

Can I update stock levels through this integration?

Yes! Use the `update_product_stock` tool. You must provide the product ID and a JSON string containing the warehouse ID and the new quantity to update your inventory.

Is the integration secure for ERP data?

Absolutely. The integration uses official Holded API keys in the request header over HTTPS. Your credentials and business data are encrypted and stored securely within the Vinkius Cloud infrastructure.

Holded MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Holded
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Holded through the 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 Holded "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Holded?"
    )
    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 Holded MCP Server

Connect your Holded ERP platform to any AI agent and take full control of your invoicing, CRM, and project management through natural conversation.

Pydantic AI validates every Holded tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through the 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

Invoicing Oversight — List all documents, retrieve detailed invoice data, and monitor payment statuses efficiently.
CRM & Contact Management — Access lists of clients, suppliers, and leads, and retrieve full profile information for better relationship management.
Project & Task Tracking — List active projects and monitor tasks across your entire portfolio to ensure deadlines are met.
Inventory & Products — Access your product catalog and update stock levels directly from the chat interface.
Business Intelligence — Retrieve account and organization metadata to maintain a high-level overview of your business operations.
Unified ERP — Bridge the gap between your accounting and operations using the comprehensive Holded API.

The Holded MCP Server exposes 11 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 Holded to Pydantic AI via MCP

Follow these steps to integrate the Holded 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 11 tools from Holded with type-safe schemas

Why Use Pydantic AI with the Holded MCP Server

Pydantic AI provides unique advantages when paired with Holded 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 Holded integration code

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

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

Holded + Pydantic AI Use Cases

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

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

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

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

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

Holded MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Holded to Pydantic AI via MCP:

get_api_profile

Retrieve information about the authenticated account

get_contact_details

Get detailed profile information for a specific contact

get_invoice_details

Get detailed information about a specific invoice

get_product_details

Get detailed information for a specific product

get_project_details

Get detailed configuration and status for a project

list_all_tasks

List tasks across all projects

list_contacts

Useful for finding the contact ID required for documents. List all contacts (clients, suppliers, leads) in Holded

list_invoices

Use this to monitor billing and find IDs for specific document actions. List all invoices in your Holded account

list_products

List all products and services in your Holded inventory

list_projects

List all active and past projects

update_product_stock

Pass details as a JSON string in "body_json" (requires warehouseId and new quantity). Update the stock level for a specific product

Example Prompts for Holded in Pydantic AI

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

"List all active projects and show the last task for each."

"Find contact 'Acme Corp' and show their recent invoices."

"Show me the details for product ID 'prod_992' and its stock level."

Troubleshooting Holded MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Holded + Pydantic AI FAQ

Common questions about integrating Holded 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 Holded MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.