Bring Referly
to Pydantic AI
Learn how to connect Referly 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 Referly MCP Server?
Connect your Referly (referly.so) account to any AI agent and take full control of your referral marketing and affiliate orchestration through natural conversation. Referly provides a powerful platform for managing partners and conversion tracking, and this integration allows you to retrieve affiliate metadata, trigger custom referral workflows, and monitor program performance directly from your chat interface.
What you can do
- Affiliate & Partner Orchestration — List all managed affiliates and retrieve detailed performance metadata, including creating new partner profiles programmatically.
- Referral & Conversion Intelligence — Track real-time conversion events and attribute sign-ups or sales to specific referral codes directly from the AI interface.
- Workflow & Automation Control — Trigger custom referral workflows and monitor their execution statuses via natural language to keep your growth loops synchronized.
- Coupon & Promo Oversight — Validate discount coupons and list active promo codes to ensure your marketing campaigns are always optimized.
- Operational Monitoring — Access analytics summaries and manage tenant metadata using simple AI commands.
How it works
1. Subscribe to this server
2. Enter your Referly Tenant ID and API Key from your dashboard at referly.so
3. Start managing your growth programs from Claude, Cursor, or any MCP-compatible client
No more manual CSV exports or attribute hunting. Your AI acts as a dedicated growth manager or affiliate coordinator.
Who is this for?
- Growth Marketers — quickly retrieve referral stats and monitor partner performance without switching apps.
- Partnership Managers — automate the onboarding of new affiliates and track their impact via natural conversation.
- Operations Teams — streamline the retrieval of conversion metadata and monitor organizational growth health directly within the chat.
Built-in capabilities (12)
Requires name and email. Create a new affiliate
Get details for a specific affiliate
Get authenticated user profile
Get referral performance summary
Check workflow execution status
List all affiliates/partners
List all discount coupons
List automation workflows
List all referral events
Track a new referral conversion
Manually trigger a workflow
Validate a discount coupon
Why Pydantic AI?
Pydantic AI validates every Referly 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 Referly integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Referly connection logic from agent behavior for testable, maintainable code
Referly in Pydantic AI
Referly and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Referly 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 Referly in Pydantic AI
The Referly 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
Referly for Pydantic AI
Every tool call from Pydantic AI to the Referly MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my AI automatically find if a specific discount code is valid in Referly?
Yes! Use the validate_coupon tool. Provide the promo code, and your agent will return its eligibility status and technical metadata instantly.
How do I find my Referly Tenant ID and API Key?
Log in to your Referly dashboard at referly.so, navigate to Settings > API Keys, and you will find your unique Tenant ID and secret API key there.
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 Referly MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai