How do I get started with OneTrust?

Subscribe, then enter your OneTrust API token (from **Admin Console → Integration → API Access**) and your base URL (e.g., app.onetrust.com or app-eu.onetrust.com). Your AI agent connects instantly. No code, no SDK — just connect and start managing privacy compliance.

Can my AI agent handle GDPR data subject access requests?

Yes. Create DSARs directly from conversation — specify the subject's name, email, and request type (access, deletion, rectification, portability, opt-out). OneTrust automatically calculates regulatory deadlines (30 days for GDPR, 45 days for CCPA) and routes the request to the right handler.

How do I check which vendors have overdue security assessments?

Ask your agent "show me vendors with overdue assessments" and it lists every third-party vendor with their risk score, questionnaire status, and last review date. You see exactly which processors need follow-up — all without logging into OneTrust or switching tabs.

Is this suitable for multi-regulation compliance (GDPR + CCPA + HIPAA)?

Absolutely. OneTrust is built for multi-regulation environments. Browse your entire data inventory mapped to processing purposes and legal bases, track DSARs across any regulation, manage privacy impact assessments, and monitor incidents with regulatory notification requirements — perfect for enterprises, healthcare organizations, and global companies operating across jurisdictions.

OneTrust MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: OneTrust
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect OneTrust through 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 OneTrust "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in OneTrust?"
    )
    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 OneTrust MCP Server

Connect your OneTrust account to any AI agent and manage privacy compliance, vendor risks, and data governance through natural conversation.

Pydantic AI validates every OneTrust 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.

What you can do

Data Subject Requests — List, create, and track DSARs (GDPR/CCPA access, deletion, opt-out requests)
Privacy Assessments — Browse PIAs, DPIAs, and Transfer Impact Assessments with risk scores
Data Inventory — View the data map: which systems process personal data, for what purpose, and under which legal basis
Vendor Risk — Manage third-party vendors with security questionnaires and risk ratings
Consent Management — Review consent purposes and cookie categories
Incident Management — Track privacy and security incidents with severity and regulatory notification status
Risk Register — View identified risks with impact, likelihood, and treatment plans

The OneTrust MCP Server exposes 10 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 OneTrust to Pydantic AI via MCP

Follow these steps to integrate the OneTrust 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 10 tools from OneTrust with type-safe schemas

Why Use Pydantic AI with the OneTrust MCP Server

Pydantic AI provides unique advantages when paired with OneTrust 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 OneTrust integration code

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

Dependency injection system cleanly separates your OneTrust connection logic from agent behavior for testable, maintainable code

OneTrust + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the OneTrust MCP Server delivers measurable value.

Type-safe data pipelines: query OneTrust with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple OneTrust tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query OneTrust and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock OneTrust responses and write comprehensive agent tests

OneTrust MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect OneTrust to Pydantic AI via MCP:

onetrust_create_dsar

Request types: ACCESS (subject wants their data), DELETION (right to be forgotten), RECTIFICATION (correct inaccurate data), PORTABILITY (data export), OPT_OUT (stop selling/sharing). The request enters the fulfillment workflow with regulatory deadlines automatically calculated (e.g., 30 days for GDPR). Create a new data subject access request in OneTrust — register a GDPR/CCPA privacy request on behalf of an individual

onetrust_get_assessment

Use for assessment review, audit evidence, or understanding the privacy risk landscape of a specific project or data processing activity. Get full details of a privacy impact assessment — questions, responses, risk findings, and recommendations from the review process

onetrust_get_dsar

15/17/20, CCPA §1798.100), processing steps completed, data sources discovered, assigned handler, deadline, and audit trail. Use for detailed DSAR investigation, compliance verification, or reporting. Get complete details of a specific data subject request — subject information, request history, fulfillment steps, and regulatory context

onetrust_list_assessments

Each shows: assessment name, type, risk score, status (Draft/In Review/Approved/Rejected), assigned owner, and completion date. Use for GDPR Art. 35 compliance, risk oversight, or assessment pipeline review. List privacy impact assessments (PIAs/DPIAs) in OneTrust — Data Protection Impact Assessments with risk scores and approval status

onetrust_list_assets

Each asset includes: name, type, data categories processed, processing purposes, legal basis, data subjects affected, retention periods, and risk classification. Essential for GDPR Art. 30 compliance. Use when the user asks about "what systems process personal data?" or needs the data map. List data inventory assets in OneTrust — applications, databases, systems, and third-party services with data classification and processing purposes

onetrust_list_consent_purposes

Each purpose includes: name, description, category (Strictly Necessary/Performance/Functional/Marketing), associated cookies/trackers, and default consent state. Purposes are the building blocks of your cookie banners and preference centers. Use for consent configuration review or privacy banner auditing. List consent purposes configured in OneTrust consent management — cookie categories, marketing preferences, and data collection purposes

onetrust_list_dsars

Each DSAR includes: subject name, email, request type (Access/Deletion/Rectification/Portability/Opt-Out), current status (Open/In Progress/Completed/Overdue), assigned handler, submission date, and regulatory deadline. Use when the user asks about pending privacy requests, DSAR compliance, or deadline tracking. List data subject access requests (DSARs) in OneTrust — GDPR, CCPA, and privacy rights requests from individuals with status and deadlines

onetrust_list_incidents

Each incident includes: title, severity (Critical/High/Medium/Low), status (Open/Under Investigation/Resolved/Closed), type (Data Breach/Near Miss/Complaint), affected data subjects count, regulatory notification status, and assigned investigator. Use for breach response management, regulatory reporting requirements, or incident trend analysis. List security and privacy incidents in OneTrust incident management — breaches, near-misses, and reports with severity and regulatory notification status

onetrust_list_risks

Each risk includes: title, description, category, impact level, likelihood score, calculated risk rating, treatment plan (Accept/Mitigate/Transfer/Avoid), associated controls, and assigned owner. Use for enterprise risk management reporting, board-level risk summaries, or identifying areas that need attention. List privacy and security risks from OneTrust risk register — identified risks with impact, likelihood, risk score, and treatment plans

onetrust_list_vendors

Each vendor shows: name, risk score, assessment status (questionnaire sent/completed/overdue), data categories shared, contractual safeguards (DPA signed/pending), and last review date. Use for vendor due diligence, subprocessor management, or GDPR Art. 28 compliance verification. List third-party vendors in OneTrust vendor risk management — data processors, subprocessors, and partners with security/privacy risk ratings

Example Prompts for OneTrust in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with OneTrust immediately.

"How many open data subject requests do we have?"

"Which vendors have overdue security assessments?"

"Show the data map for our CRM system."

Troubleshooting OneTrust MCP Server with Pydantic AI

Common issues when connecting OneTrust to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

OneTrust + Pydantic AI FAQ

Common questions about integrating OneTrust 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 OneTrust MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.