How do I find my Atlas.so API Token?

Log in to your Atlas dashboard, go to **App Configuration > Data > API**, and you will find your API Token there.

Can I see help center articles via this server?

Yes, use the `list_articles` tool to retrieve a list of articles from your Atlas help center.

How are customer IDs handled?

Atlas uses unique internal IDs for customers. You can discover these IDs by using the `list_customers` tool or searching for a specific customer by email.

Atlas MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Atlas
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Atlas 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 Atlas "
            "(8 tools)."
        ),
    )

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

The Atlas MCP Server provides a seamless natural language interface to your Atlas.so customer support platform. Empower your AI agent to manage your entire support operation, from ticket auditing to customer oversight and knowledge base access.

Pydantic AI validates every Atlas tool response against typed schemas, catching data inconsistencies at build time. Connect 8 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.

Key Features

Ticket Management — List all active support tickets, retrieve detailed conversation metadata, and create new tickets directly from your chat.
Customer Oversight — Access and manage your customer database, including names, emails, and internal IDs.
Knowledge Base Access — List help center articles to provide accurate information based on your organization's documentation.
Team Monitoring — View a list of team users (agents) to understand your support capacity.
Real-time Support Analytics — Quickly audit active conversations and customer needs using simple natural language commands.
Secure API Integration — Uses your Atlas.so API Token for safe and authenticated access to your support data.

The Atlas MCP Server exposes 8 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 Atlas to Pydantic AI via MCP

Follow these steps to integrate the Atlas 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 8 tools from Atlas with type-safe schemas

Why Use Pydantic AI with the Atlas MCP Server

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

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

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

Atlas + Pydantic AI Use Cases

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

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

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

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

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

Atlas MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Atlas to Pydantic AI via MCP:

create_ticket

Create a new support ticket

get_account_check

Verify Atlas account connection

get_customer

Get details for a specific customer

get_ticket

Get details for a specific ticket

list_articles

List help center articles

list_customers

List all customers in Atlas

list_tickets

List all support tickets in Atlas

list_users

List team users (agents)

Example Prompts for Atlas in Pydantic AI

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

"List all active support tickets in Atlas."

"Show me the details for ticket ID 'tick_12345'."

"Find all help articles related to 'Pricing'."

Troubleshooting Atlas MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Atlas + Pydantic AI FAQ

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