Can I block a fraudulent user through the agent?

Yes! Use the `apply_user_decision` tool with the user's ID and the appropriate decision ID (like `block_user`). The action will be applied in Sift immediately.

How do I check the risk score for a specific customer?

Use the `get_user_fraud_score` tool with the customer's unique ID. Your agent will fetch the latest risk score generated by Sift's machine learning models.

Where do I find my Sift API Key and Account ID?

Log in to your Sift Dashboard and navigate to **Settings -> API Keys**. You will find your REST API Key and Account ID there.

Sift (Chargeback) MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Sift (Chargeback)
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Sift (Chargeback) through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Sift (Chargeback) "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Sift (Chargeback)?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Sift (Chargeback) MCP Server

Connect your Sift account to any AI agent and take full control of your fraud protection and chargeback management through natural conversation. Streamline risk analysis and dispute resolution.

Pydantic AI validates every Sift (Chargeback) tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through the 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.

What you can do

Chargeback Reporting — Notify Sift of new chargeback events, including states and reasons natively
Fraud Intelligence — Retrieve real-time fraud scores for users to evaluate transaction risk flawlessly
Decision Automation — Apply manual or automated decisions (e.g., block user, accept order) securely
Dispute Oversight — List and audit the history of decisions and labels applied to any user flawlessly
Workflow Visibility — Access and monitor your configured fraud prevention workflows in real-time
Behavioral Tracking — Log custom events like logins or transactions to refine Sift's machine learning directly within your workspace

The Sift (Chargeback) MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Sift (Chargeback) to Pydantic AI via MCP

Follow these steps to integrate the Sift (Chargeback) MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Sift (Chargeback) with type-safe schemas

Why Use Pydantic AI with the Sift (Chargeback) MCP Server

Pydantic AI provides unique advantages when paired with Sift (Chargeback) through the Model Context Protocol.

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 Sift (Chargeback) integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Sift (Chargeback) connection logic from agent behavior for testable, maintainable code

Sift (Chargeback) + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Sift (Chargeback) MCP Server delivers measurable value.

Type-safe data pipelines: query Sift (Chargeback) with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Sift (Chargeback) tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Sift (Chargeback) and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Sift (Chargeback) responses and write comprehensive agent tests

Sift (Chargeback) MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Sift (Chargeback) to Pydantic AI via MCP:

apply_user_decision

Apply a manual decision to a user (e.g. block_user)

get_user_fraud_labels

Retrieve labels (e.g. $bad, $good) applied to a user

get_user_fraud_score

Get the current fraud score for a user

list_sift_decisions

List available decisions (actions) in Sift

list_sift_workflows

List configured fraud prevention workflows

list_user_decision_history

List the history of decisions applied to a user

report_sift_chargeback

Report a chargeback event to Sift

track_sift_event

Track a general event (e.g. $login, $transaction) in Sift

Example Prompts for Sift (Chargeback) in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Sift (Chargeback) immediately.

"What is the fraud score for user 'user_abc_123'?"

"Report a chargeback for order #999 from user 'user_789' as '$fraud'."

"Show me the last 5 decisions applied to user 'user_456'."

Troubleshooting Sift (Chargeback) MCP Server with Pydantic AI

Common issues when connecting Sift (Chargeback) to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Sift (Chargeback) + Pydantic AI FAQ

Common questions about integrating Sift (Chargeback) MCP Server with Pydantic AI.

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 Sift (Chargeback) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.