Data protection

One policy engine enabling enterprises to inspect, transform, or block sensitive data at every prompt, tool call, tool response, and answer.

Works with both Barndoor LLM Gateway and MCP Governance

You set the policies. Barndoor enforces them.

Prevent PII leaks, social engineering attempts, prompt injections, data exfiltration, and more.

LLM Gateway

LLM prompt

WHAT GETS CAUGHT

PII, credentials, API keys, sensitive data, and more

LLM response

WHAT GETS CAUGHT

Generated PII, policy violations, sensitive data in outputs, and more

MCP Governance

MCP tool input

WHAT GETS CAUGHT

Confidential data exfiltration, indirect prompt injection, malicious instructions, and more

MCP tool output

WHAT GETS CAUGHT

PII, confidential files, data exfiltration to third-party servers, and more

Enforce data protection across every prompt, tool call, and response

METHODOLOGY

How it works

Detects

Pattern-based

regex

Built-in classifiers for well-formed values used to match character combinations in strings.

• credit card
• SSN
• phone
• email
• IBAN
• API keys
• IP address
• Passport number
• DOB
• VIN

Model-based

transformer

Natural language classifiers that read surrounding context. Same mechanism powers prompt detection.

• PII in context
• prompt security
• allow lists or overrides
• insider threat signal
• data exfiltration intent
• social engineering attempts
• jailbreak attempts

Custom

user-defined

Your own patterns or example-based for formats specific to your business. Configured in the policy editor.

• internal IDs
• order numbers
• customer records
• employee IDs
• invoice numbers
• SKU codes
• policy numbers
• membership IDs
• ticket numbers
• account numbers

Key capabilities

PII, secrets, injections under one policy

Detection groups bundle SSNs, cloud keys, API tokens, DB credentials, and prompt injection patterns into a single reusable rule you attach to any enforcement policy.

Enforce data policies across any LLM or MCP server

Data protection designed for agents, connected MCP, and any model.

Apply data policy by person, groups, and roles

Scope enforcement to specific groups and roles based on your identity provider.

Enterprise data protection across LLMs and MCPs

CAPABILITY

LLM Gateway

Detection & Redaction

• PII & credential detection
• Tokenize, mask, redact, omit
• Custom detectors
• Direct prompt injection & jailbreak detection

Who Policies Apply To

• All users
• Groups via IdP
• Agents & service identities

Solution Scope

• Per-model

MCP Governance

Detection & Redaction

• PII & credential detection
• Tokenize, mask, redact, omit
• Custom detectors
• Indirect prompt injection detection

Who Policies Apply To

• All users
• Groups via IdP
• Agents & service identities

Solution Scope

• Per-tool / per-MCP server
• Metadata-condition policies

Detection & Redaction

Inspect prompts, responses, and tool I/O for sensitive content.

• PII & credential detection
• Regex + transformer detectors
• Tokenize, mask, redact, omit
• Per-field redaction options
• Custom detectors
• Direct prompt injection & jailbreak detection

WHO POLICIES APPLY TO

Identity-aware scoping powered by your IdP.

• All users
• Groups via IdP
• Okta, Azure AD, Google Workspace
• Non-human callers, scoped credentials

SOLUTION SCOPE

Where each policy can target

• Per-model
• Per-tool / per-MCP server
• Metadata-condition policies

Built for enterprise environments

Deploy Barndoor where you need it—with the architecture and controls your organization requires.

SaaS

Fully managed deployment for fast setup and ongoing updates.

Private Cloud

Deployed in your cloud environment to meet security and compliance requirements.

On-Prem

Run entirely within your infrastructure for maximum control and data residency.

Frequently asked questions

• How do AI agents leak sensitive data through MCP tool calls?

AI agents can leak sensitive data through MCP when they pass context they’ve already retrieved, including customer records, internal documents, account numbers, etc.

• What is indirect prompt injection in MCP, and how does Barndoor prevent it?

Indirect prompt injection is when malicious instructions are embedded inside content an agent retrieves, which the agent then follows. Barndoor MCP Governance runs a transformer-based classifier on every tool output before that content reaches the model.

• Does an LLM gateway protect data that flows through MCP tool calls?

No, an LLM gateway governs what goes to the model and comes back, while MCP tool calls are a separate traffic surface. Barndoor MCP Governance covers the tool surfaces.

• What transformation options does Barndoor data protection apply to MCP and how do I choose among them?

Barndoor data protection offers several transformation options for MCP tool traffic, including blocking, redacting, masking, and tokenizing.