Bring Sql Database
to Pydantic AI
Learn how to connect Directus to Pydantic AI and start using 16 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Directus MCP Server?
Connect your Directus instance to any AI agent and manage your content database through natural conversation.
What you can do
- Collection Management — List all data collections with field counts and inspect individual collection schemas
- Content CRUD — Create, read, update, and delete items in any collection using JSON payloads
- Search & Query — Search items within collections by keyword to find specific content quickly
- Schema Inspection — List all fields and their data types for any collection to understand your data model
- File Management — Browse uploaded files and retrieve metadata for specific assets
- User & Role Management — List all users with roles and status, view role configurations, and check your own profile
- Audit Trail — Access the activity log of recent database operations for compliance and debugging
How it works
1. Subscribe to this server
2. Enter your Directus Static Token from your user profile in the Data Studio
3. Start managing your content from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Content Teams — create, update, and search content items across collections without opening the Directus dashboard
- Developers — inspect collection schemas, manage fields, and debug data issues through conversational AI
- Administrators — audit user activity, manage roles, and monitor database operations
Built-in capabilities (16)
Verify connectivity
Create an item
Delete an item
Get collection details
Get file details
Get item details
Get current user
List recent activity
List collections
List fields
List files
List items
List roles
List users
Search items
Update an item
Why Pydantic AI?
Pydantic AI validates every Directus tool response against typed schemas, catching data inconsistencies at build time. Connect 16 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 Directus integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Directus connection logic from agent behavior for testable, maintainable code
Directus in Pydantic AI
Directus and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Directus 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 Directus in Pydantic AI
The Directus 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 16 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
Directus for Pydantic AI
Every tool call from Pydantic AI to the Directus MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I create, update, and delete content items in any collection?
Yes! Use create_item with a collection name and JSON payload to add new items. Use update_item with the collection, item ID, and updated fields to modify existing items. Use delete_item to remove items. All operations respect the permissions assigned to your Static Token's user role.
How does Directus authentication work with a Static Token?
Directus uses a non-expiring Static Token associated with a specific user account. Generate it from your User Profile in the Data Studio. The token is sent as a Bearer token in the Authorization header. Its permissions match the role assigned to that user — use an admin role for full access or a restricted role for read-only operations.
Can I audit what changes have been made to my database?
Yes. The list_activity tool retrieves the audit log of recent database operations, showing who made changes, which collections were affected, timestamps, and the type of operation (create, update, delete). Combine with list_users and list_roles for full accountability tracking.
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 Directus MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai