Pydantic AISDK

Onfido MCP Server

Bring Identity Verification
to Pydantic AI

Name: Onfido MCP Server
Price: 29 USD
Availability: InStock
Rating: 5.0 (1 reviews)
Author: Vinkius

Learn how to connect Onfido to Pydantic AI and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.

GDPR Free for Subscribers

Create ApplicantCreate CheckCreate Workflow RunGet ReportGet Workflow RunRegister Webhook

Unlock for AI Agents

Ask AI about this MCP Server ChatGPT Claude Perplexity

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

What is the Onfido MCP Server?

Connect your Onfido account to any AI agent to streamline your KYC (Know Your Customer) and identity verification processes through natural conversation.

What you can do

Applicant Management — Create and manage applicant profiles representing individuals undergoing verification.
Workflow Studio Integration — Start and monitor complex verification workflows (Workflow Runs) to automate multi-step identity checks.
Legacy Checks — Create classic checks for specific report combinations like document verification and facial similarity.
Detailed Reporting — Retrieve comprehensive verification reports, including results and granular breakdowns of identity data.
Real-time Notifications — Register webhooks to receive asynchronous updates on verification statuses directly to your systems.

How it works

Subscribe to this server
Enter your Onfido API Token
Start managing identity verifications from Claude, Cursor, or any MCP-compatible client

Who is this for?

Compliance Officers — instantly check the status of an applicant's verification or review report breakdowns without manual dashboard searching.
Fintech Developers — integrate and test identity verification flows directly from the code editor or terminal.
Operations Teams — automate the creation of applicants and trigger verification workflows as part of user onboarding.

Built-in capabilities (6)

create_applicant

Create a new Onfido applicant

create_check

Create a new Check (Legacy/Classic)

create_workflow_run

Create a new Workflow Run

get_report

Retrieve a Verification Report

get_workflow_run

g., awaiting_input, processing, approved, review, declined). Retrieve a Workflow Run

register_webhook

Why Pydantic AI?

Pydantic AI validates every Onfido tool response against typed schemas, catching data inconsistencies at build time. Connect 6 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 Onfido integration code
—
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
—
Dependency injection system cleanly separates your Onfido connection logic from agent behavior for testable, maintainable code

See it in action

Onfido in Pydantic AI

AI Agent→Vinkius

High Security·Kill Switch·Plug and Play

Why Vinkius

Onfido and 4,000+ other MCP servers. One platform. One governance layer.

Teams that connect Onfido 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.

4,000+MCP Servers ready

<40msCold start

60%Token savings

	Raw MCP	Vinkius
Server catalog	Find and host yourself	4,000+ 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

Unlock for AI Agents View step-by-step setup guide for Pydantic AI →

Enterprise Security

Why teams choose Vinkius for Onfido in Pydantic AI

The Onfido 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 6 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.

Unlock for AI Agents View full Onfido details →

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

The Vinkius Advantage

How Vinkius secures
Onfido for Pydantic AI

Every tool call from Pydantic AI to the Onfido MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.

< 40msCold start

Ed25519Signed audit chain

60%Token savings

FAQ

Frequently asked questions

How can I check the current status of a verification process?

Use the get_workflow_run tool with the specific Workflow Run ID. It will return the current state, such as 'awaiting_input', 'processing', 'approved', or 'declined'.

Can I create a verification check without using Workflow Studio?

Yes. Use the create_check tool for legacy integrations. You can specify a comma-separated list of report names, such as 'document, facial_similarity_photo', for a specific applicant ID.

How do I get notified when a report is completed?

You can use the register_webhook tool to set up a listener URL for specific events like 'report.completed', 'check.completed', or 'workflow_run.completed'.

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 Onfido MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.