Bring Site Search
to Pydantic AI
Learn how to connect Constructor to Pydantic AI and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the Constructor MCP Server?
Connect your Constructor.io account to any AI agent and take full control of your site search and product discovery workflows through natural conversation.
What you can do
- AI-Powered Search — Execute ML-ranked product retrieval dynamically mapped to e-commerce signals and user intent
- Predictive Autocomplete — Access fast predictive typing boundaries and trace exact matched categories for any partial query
- Dynamic Recommendations — Surface personalized products using collaborative filtering models and custom recommendation pods
- Category & Brand Browsing — Navigate through product directory trees and manufacturer taxonomies without any query bias
- Advanced Filtering — Apply strict attribute filters (colors, sizes, features) and custom sort rules to refine product discovery results
- Collection Management — Retrieve curated marketing clusters and static collections accurately for promotional auditing
How it works
1. Subscribe to this server
2. Enter your Constructor.io Public API Key (found in Dashboard > Integration)
3. Start optimizing your e-commerce discovery from Claude, Cursor, or any MCP-compatible client
Who is this for?
- E-commerce Managers — audit search rankings and recommendation pods without manual dashboard testing
- Product Owners — monitor category browsing performance and verify attribute filtering logic in real-time
- Developers — test and debug search API parameters and personalized recommendation outputs through natural language
- Marketing Teams — verify that curated collections and brand taxonomies are correctly mapped and rankable
Built-in capabilities (10)
Perform structural extraction of properties driving active Account logic
Inspect deep internal arrays mitigating specific Plan Math
Provision a highly-available JSON Payload generating hard Customer bindings
Identify precise active arrays spanning native Gateway auth
Identify precise active arrays spanning native Hold parsing
Retrieve explicit Cloud logging tracing explicit Vault limits
]` bounding JSON structures restricting arrays to exact colors/sizes or features. Irreversibly vaporize explicit validations extracting rich Churn flags
Dispatch an automated validation check routing explicit Gateway history
Identify bounded CRM records inside the Headless Constructor.io Platform
Enumerate explicitly attached structured rules exporting active Billing
Why Pydantic AI?
Pydantic AI validates every Constructor tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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 Constructor integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Constructor connection logic from agent behavior for testable, maintainable code
Constructor in Pydantic AI
Constructor and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Constructor 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 Constructor in Pydantic AI
The Constructor 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 10 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
Constructor for Pydantic AI
Every tool call from Pydantic AI to the Constructor MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my agent check the ML ranking for a specific product search?
Yes. Use the 'search_products' tool. The agent will retrieve results ranked by Constructor's ML engine, allowing you to audit how products are surfaced based on specific keywords and intent signals.
How do I retrieve personalized recommendations via the agent?
Provide the 'pod_id' to your agent and use the 'get_recommendations' tool. The agent will query the collaborative filtering models to return a list of products tailored to your specified recommendation logic.
Can I test attribute filtering like color or size through chat?
Absolutely. The 'search_filtered' tool allows you to pass exact attribute mappings (e.g., 'color:blue,size:L'). Your agent will verify how the API restricts results to those specific structural bounds.
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 Constructor MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai