> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# Third-Party APIs

> Reference for third-party API integrations that connect with managed services for guardrail use cases.

Third-party APIs connect with managed services for a wide variety of guardrail use cases.
Combine techniques across the guardrail ecosystem for a best-of-breed approach.

## ActiveFence

The NeMo Guardrails library supports using the [ActiveFence ActiveScore API](https://docs.activefence.com/index.html) as an input and output rail out-of-the-box (you need to have the `ACTIVEFENCE_API_KEY` environment variable set).

### Example usage

```yaml
rails:
  input:
    flows:
      - activefence moderation on input
  output:
    flows:
      - activefence moderation on output
```

For more details, check out the [ActiveFence Integration](/configure-guardrails/guardrail-catalog/third-party/active-fence) page.

## PolicyAI

The NeMo Guardrails library supports using [PolicyAI](https://musubilabs.ai) by Musubi Labs as an input and output rail out-of-the-box (you need to have the `POLICYAI_API_KEY` environment variable set).

PolicyAI provides policy-based content moderation, allowing you to define custom policies and organize them with tags for environment-based management.

### Example usage

```yaml
rails:
  input:
    flows:
      - policyai moderation on input
  output:
    flows:
      - policyai moderation on output
```

For more details, check out the [PolicyAI Integration](/configure-guardrails/guardrail-catalog/third-party/policyai) page.

## AutoAlign

The NeMo Guardrails library supports using the AutoAlign's guardrails API (you need to have the `AUTOALIGN_API_KEY` environment variable set).

### Example usage

```yaml
rails:
  input:
    flows:
      - autoalign check input
  output:
    flows:
      - autoalign check output
```

For more details, check out the [AutoAlign Integration](/configure-guardrails/guardrail-catalog/third-party/auto-align) page.

## Clavata

The NeMo Guardrails library supports using [Clavata AI](https://docs.clavata.ai/) as an input and output rail out-of-the-box (you need to have the CLAVATA\_API\_KEY environment variable set).

### Example usage

```yaml
rails:
  config:
    clavata:
      policies:
        Fraud: 00000000-0000-0000-0000-000000000000
        Bot_Behavior: 00000000-0000-0000-0000-000000000000
      label_match_logic: ANY

```

For more details, check out the [Clavata Integration](/configure-guardrails/guardrail-catalog/third-party/clavata) page.

## Cleanlab

The NeMo Guardrails library supports using the [Cleanlab Trustworthiness Score API](https://cleanlab.ai/blog/trustworthy-language-model/) as an output rail (you need to have the `CLEANLAB_API_KEY` environment variable set).

### Example usage

```yaml
rails:
  output:
    flows:
      - cleanlab trustworthiness
```

For more details, check out the [Cleanlab Integration](/configure-guardrails/guardrail-catalog/third-party/cleanlab) page.

## GCP Text Moderation

The NeMo Guardrails library supports using the GCP Text Moderation. You need to be authenticated with GCP, refer [here](https://cloud.google.com/docs/authentication/application-default-credentials) for auth details.

### Example usage

```yaml
rails:
  input:
    flows:
      - gcpnlp moderation
```

For more details, check out the [GCP Text Moderation](/configure-guardrails/guardrail-catalog/third-party/gcp-text-moderations) page.

## GuardrailsAI Integration

The NeMo Guardrails library supports using [GuardrailsAI validators](https://github.com/guardrails-ai/guardrails) for comprehensive input and output validation. GuardrailsAI provides a wide range of validators for content safety, PII detection, toxic language filtering, jailbreak detection, and more.

### Example usage

```yaml
rails:
  config:
    guardrails_ai:
      validators:
        - name: toxic_language
          parameters:
            threshold: 0.5
        - name: guardrails_pii
          parameters:
            entities: ["phone_number", "email", "ssn"]
  input:
    flows:
      - guardrailsai check input $validator="guardrails_pii"
  output:
    flows:
      - guardrailsai check output $validator="toxic_language"
```

For more details, check out the [GuardrailsAI Integration](/configure-guardrails/guardrail-catalog/third-party/guardrails-ai) page.

## Fiddler Guardrails for Safety and Hallucination Detection

The NeMo Guardrails library supports using [Fiddler Guardrails](https://docs.fiddler.ai/protection/guardrails) for safety and hallucination detection in input and output flows.

In order to access Fiddler guardrails, you need access to a valid Fiddler environment, and a [Fiddler environment key](https://docs.fiddler.ai/protection/guardrails). You'll need to set the `FIDDLER_API_KEY` environment variable to authenticate into the Fiddler service.

```yaml
rails:
  config:
    fiddler:
      server_endpoint: https://testfiddler.ai # Replace this with your fiddler environment

```

### Example usage

```yaml
rails:
    config:
        fiddler:
            fiddler_endpoint: https://testfiddler.ai # Replace this with your fiddler environment
    input:
        flows:
            - fiddler user safety
    output:
        flows:
            - fiddler bot safety
            - fiddler bot faithfulness

```

For more details, check out the [Fiddler Integration](/configure-guardrails/guardrail-catalog/third-party/fiddler) page.

## Prompt Security Protection

The NeMo Guardrails library supports using [Prompt Security API](https://prompt.security/?utm_medium=github\&utm_campaign=nemo-guardrails) for protecting input and output retrieval flows.

To activate the protection, you need to set the `PS_PROTECT_URL` and `PS_APP_ID` environment variables.

### Example usage

```yaml
rails:
  input:
    flows:
      - protect prompt
  output:
    flows:
      - protect response
```

For more details, check out the [Prompt Security Integration](/configure-guardrails/guardrail-catalog/third-party/prompt-security) page.

## CrowdStrike AIDR

The NeMo Guardrails library supports using CrowdStrike AIDR for protecting data and interactions with LLMs within
AI-powered applications.

### Example usage

```yaml
rails:
  input:
    flows:
      - crowdstrike aidr guard input

  output:
    flows:
      - crowdstrike aidr guard output
```

For more details, check out the [CrowdStrike AIDR Integration](/configure-guardrails/guardrail-catalog/third-party/crowdstrike-aidr) page.

## Pangea AI Guard

> **Warning:** The Pangea AI Guard integration is deprecated and will be removed in a future release.
> Users should migrate to the CrowdStrike AIDR integration.

The NeMo Guardrails library supports using [Pangea AI Guard](https://pangea.cloud/services/ai-guard/) for protecting data and
interactions with LLMs within AI-powered applications.

### Example usage

```yaml
rails:
  input:
    flows:
      - pangea ai guard input

  output:
    flows:
      - pangea ai guard output
```

For more details, check out the [Pangea AI Guard Integration](/configure-guardrails/guardrail-catalog/third-party/pangea) page.

## Trend Micro Vision One AI Application Security

The NeMo Guardrails library supports using
[Trend Micro Vision One AI Guard](https://docs.trendmicro.com/en-us/documentation/article/trend-vision-one-ai-scanner-ai-guard) for protecting input and output flows within AI-powered applications.

### Example usage

```yaml
rails:
  input:
    flows:
      - trend ai guard input
  output:
    flows:
      - trend ai guard output
```

For more details, check out the [Trend Micro Vision One AI Application Security](/configure-guardrails/guardrail-catalog/third-party/trend-micro) page.

## Cisco AI Defense

The NeMo Guardrails library supports using [Cisco AI Defense Inspection](https://www.cisco.com/site/us/en/products/security/ai-defense/index.html?utm_medium=github\&utm_campaign=nemo-guardrails) for protecting input and output flows.

To activate the protection, you need to set the `AI_DEFENSE_API_KEY` and `AI_DEFENSE_API_ENDPOINT` environment variables.

### Example usage

```yaml
rails:
  input:
    flows:
      - ai defense inspect prompt

  output:
    flows:
      - ai defense inspect response
```

For more details, check out the [Cisco AI Defense Integration](/configure-guardrails/guardrail-catalog/third-party/ai-defense) page.

## HuggingFace Classifier

The NeMo Guardrails library supports using HuggingFace text classification models for fast, prompt-free content moderation on input, output, and retrieval flows. Classifiers can run locally via `transformers` or connect to remote inference servers (vLLM, KServe, FMS).

### Example usage

To set up a local HuggingFace classifier rail for named entity recognition on input and output flows:

```yaml
rails:
  config:
    hf_classifier:
      named_entity_recognition:
        engine: local
        model: dslim/distilbert-NER
        task: token-classification
        threshold: 0.7
        blocked_labels:
          - "PER"
          - "LOC"
          - "ORG"
        parameters:
          aggregation_strategy: simple

  input:
    flows:
      - hf classifier check input $classifier=named_entity_recognition
  output:
    flows:
      - hf classifier check output $classifier=named_entity_recognition
```

For more details, check out the [HuggingFace Classifier Integration](/configure-guardrails/guardrail-catalog/third-party/hf-classifier) page.

> Reference for third-party API integrations that connect with managed services for guardrail use cases.

## Docs

- [ActiveFence Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/active-fence.md)
- [AlignScore Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/alignscore.md)
- [AutoAlign Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/auto-align.md)
- [Cisco AI Defense Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/ai-defense.md)
- [Clavata Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/clavata.md)
- [Cleanlab Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/cleanlab.md)
- [CrowdStrike AIDR integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/crowdstrike-aidr.md)
- [F5 Guardrails Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/f5-ai-guardrails.md)
- [Fiddler Guardrails Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/fiddler.md)
- [GCP Text Moderation Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/gcp-text-moderations.md)
- [GLiNER Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/gliner.md)
- [GuardrailsAI Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/guardrails-ai.md)
- [HuggingFace Classifier Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/hf-classifier.md)
- [Llama-Guard Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/llama-guard.md)
- [Pangea AI Guard integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/pangea.md)
- [Patronus Evaluate API Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/patronus-evaluate-api.md)
- [Patronus Lynx Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/patronus-lynx.md)
- [PolicyAI Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/policyai.md)
- [Polygraf Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/polygraf.md)
- [Presidio Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/presidio.md)
- [Private AI Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/privateai.md)
- [Prompt Security Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/prompt-security.md)
- [Regular Expression Detection Integration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/regex.md)
- [Trend Micro Vision One AI Application Security](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/guardrail-catalog/third-party/trend-micro.md)