How to Use the Zammad MCP in Pydantic AI

Q: How does Pydantic AI handle the process of creating new tickets with Zammad?

It's highly validated. When your agent calls createticket, Pydantic ensures all required fields are present and correctly typed before the action hits Zammad, preventing bad data writes.

Q: Can Pydantic AI assist with updating user profiles in Zammad?

Yes. Use updateuser to change details on an existing account in Zammad. Because of Pydantic's validation, you know the data structure is correct before the update runs.

Q: What data types can I scrub privacy-wise using Pydantic AI with Zammad?

You work with User records for deletion. The dataprivacydeleteuser tool is designed to handle user account removal from Zammad while maintaining strict type validation.

Q: Does Pydantic AI support listing all available Zammad roles?

Absolutely. You can call listroles to retrieve a clean, validated list of every role defined within your Zammad instance for the agent to reference.

Type-safe Zammad automation with Pydantic AI, guaranteeing correctness for your agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zammad MCP to Pydantic AI

Create your Vinkius account to connect Zammad 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 Zammad with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create and modify support tickets.

The `create_ticket` tool lets your agent generate a new Zammad ticket. For existing issues, use `update_ticket` to change the details or status safely. You can also append context using `list_ticket_articles` followed by `create_ticket_article`, ensuring every note is linked directly back to its source in Zammad.

Manage user accounts and permissions.

Your agent handles identity via structured tools. It can create new users with `create_user` or fetch details using `get_user`. If an account needs retiring, `data_privacy_delete_user` executes the safe deletion process. You'll also use `list_roles` to see all available permissions and validate what your agent is allowed to do in Zammad.

Retrieve complex system object details.

Need a full view of an organization? Use `get_organization` for deep details on any Zammad company. You can also check group information with `get_group`, which returns structured data. Keep track of tags across objects using `list_tags_for_object`. This method lets your agent list all associated tags (like 'Billing') for a specific resource type in Zammad.

Setup guide

Set up Zammad 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": {
        "zammad-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Zammad 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 Zammad. 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 Zammad 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 Zammad MCP in Pydantic AI

It's highly validated. When your agent calls `create_ticket`, Pydantic ensures all required fields are present and correctly typed before the action hits Zammad, preventing bad data writes.

Yes. Use `update_user` to change details on an existing account in Zammad. Because of Pydantic's validation, you know the data structure is correct before the update runs.

You work with User records for deletion. The `data_privacy_delete_user` tool is designed to handle user account removal from Zammad while maintaining strict type validation.

Absolutely. You can call `list_roles` to retrieve a clean, validated list of every role defined within your Zammad instance for the agent to reference.

This server touches User records. To ensure compliance, you must use `data_privacy_delete_user` to perform a controlled deletion of user accounts within Zammad.

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