Bring It Documentation
to Pydantic AI
Learn how to connect Hudu to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Hudu MCP Server?
Connect your Hudu instance to any AI agent and manage your IT documentation through natural conversation.
What you can do
- Company Management — List all client companies, inspect profiles, and create new company records
- Asset Tracking — Browse all assets (servers, workstations, network devices), filter by company, inspect details, and create new asset records with tags
- Password Vault — List stored passwords filtered by company, and securely retrieve individual password entries with secrets
- Knowledge Base — Browse all articles and read full content with metadata for any specific article
- Procedures & Checklists — List all procedures filtered by company and inspect detailed steps for operational checklists
How it works
1. Subscribe to this server
2. Enter your Hudu Instance URL and API Key
3. Start managing IT documentation from Claude, Cursor, or any MCP-compatible client
Who is this for?
- MSPs (Managed Service Providers) — access client documentation, passwords, and asset inventories without opening the Hudu portal
- IT Administrators — track assets, review procedures, and manage knowledge base articles through AI
- Support Engineers — quickly retrieve client passwords, asset details, and troubleshooting procedures during incidents
Built-in capabilities (12)
Requires asset name and company ID. Create a new asset
Requires a name. Create a new company
Get details for a specific article
Get details for a specific asset
Get details for a specific company
Get details for a specific password
Get details for a specific procedure
List knowledge base articles
Can be filtered by company ID. List assets
List all companies in Hudu
Can be filtered by company ID. List passwords
Can be filtered by company ID. List procedures
Why Pydantic AI?
Pydantic AI validates every Hudu tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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 Hudu integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Hudu connection logic from agent behavior for testable, maintainable code
Hudu in Pydantic AI
Hudu and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Hudu 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 | 3,400+ 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 Hudu in Pydantic AI
The Hudu 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 12 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
Hudu for Pydantic AI
Every tool call from Pydantic AI to the Hudu MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I retrieve stored passwords for a specific client?
Yes. Use list_passwords with an optional company_id to filter passwords by client. Then use get_password with a specific password ID to retrieve the full entry including the secret. Use list_companies to find the company ID first.
Does Hudu require a custom instance URL?
Yes. Hudu is self-hosted or uses dedicated instances, so you need to provide your Instance URL (e.g., https://your-company.huducloud.com) along with the API Key. The API Key is sent via the x-api-key header (not Bearer), and all API calls are routed to {instanceUrl}/api/v1.
Can I track all assets for a specific company?
Yes. Use list_assets with the company_id parameter to retrieve all assets (servers, workstations, network devices) for a specific client. Use get_asset for detailed specifications and tags. Use create_asset to add new assets with a name, company ID, and optional asset tag.
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 Hudu MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai