Compatible with every major AI agent and IDE
What is the Zammad MCP Server?
Connect your Zammad helpdesk to any AI agent to streamline your customer support and user management through natural conversation.
What you can do
- Ticket Management — List, retrieve, and create tickets to stay on top of customer requests using
list_ticketsandget_ticket. - User & Organization Control — Search, create, and update user profiles and organizational data with tools like
search_usersandlist_organizations. - Group & Role Insights — List and search through system groups and roles to understand permissions and assignments.
- Data Privacy — Securely handle user deletions via specialized data privacy tasks using
data_privacy_delete_user.
How it works
- Subscribe to this server
- Enter your Zammad URL and Personal Access Token
- Start managing your helpdesk from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Support Leads — quickly get ticket statuses and user history without switching tabs.
- System Admins — manage users, groups, and organizations directly from the terminal or AI interface.
- DevOps Engineers — integrate helpdesk data into automated workflows and reporting.
Built-in capabilities (41)
Add a tag to an object
Create a new Zammad ticket
Create a new article on a ticket
Create a new Zammad user
Delete a user via Data Privacy task (Recommended over direct delete)
Delete a Zammad ticket
Delete a Zammad user
Get details for a specific Zammad group
Get links for a specific object
Get current Zammad user details
Get details for a specific Zammad organization
Get shared draft for a ticket
Get details for a specific Zammad ticket
Get details for a specific ticket article
Get details for a specific Zammad user
List all tags in the system (Admin)
List calendars
List checklist items
List checklist templates
List checklists
List all Zammad groups
List mentions
List all Zammad organizations
List all Zammad roles
List SLAs
List tags for a specific object (e.g., Ticket)
List articles for a specific ticket
List ticket priorities
List ticket states
List Zammad tickets
List time accountings for a ticket
List all Zammad users
Remove a tag from an object
Search for groups in Zammad
Search for organizations in Zammad
Search for roles in Zammad
Search for tickets in Zammad
Search for users in Zammad
Trigger async generation of a ticket summary
Update an existing Zammad ticket
Update an existing Zammad user
Why Pydantic AI?
Pydantic AI validates every Zammad tool response against typed schemas, catching data inconsistencies at build time. Connect 41 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.
- —
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 Zammad integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Zammad connection logic from agent behavior for testable, maintainable code
Zammad in Pydantic AI
Zammad and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Zammad to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Zammad in Pydantic AI
The Zammad 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. All 41 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* 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
How Vinkius secures
Zammad for Pydantic AI
Every tool call from Pydantic AI to the Zammad MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search for specific users or organizations within Zammad?
Yes! You can use the search_users and search_organizations tools to find specific records using search queries directly from your AI agent.
How do I safely delete a user according to data privacy standards?
It is recommended to use the data_privacy_delete_user tool. This initiates a Data Privacy task in Zammad, which is the preferred method over direct deletion for compliance.
Can I view my own Zammad profile details?
Yes, the get_me tool allows you to retrieve the profile details of the currently authenticated user associated with your access token.
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 Zammad MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
AdButler
5 toolsAd serving and reporting — manage publishers, zones, campaigns, and ad performance via AI.

Gorgias
12 toolsManage your customer support tickets, messages, and user profiles via AI.

RudderStack
7 toolsConnect your AI assistant natively to RudderStack to effortlessly monitor global data sources, trace routing connections, and audit enterprise marketing audiences via structured text commands.

Avalara (AvaTax)
10 toolsAutomate tax calculation and compliance with Avalara AvaTax — calculate rates and resolve addresses via AI.
