skills.rest
truefoundry
truefoundryOFFICIAL
Explore all skills by this author →
Website𝕏@truefoundryGitHub

truefoundry-guardrails

Configure content safety guardrails for the TrueFoundry AI Gateway.

13|Updated Feb 13, 2026
Search Tags:#security#mcp#moderation#guardrails#content-safety#gateway#pii-detection
One-click install
npx skills add https://github.com/truefoundry/tfy-gateway-skills --skill truefoundry-guardrails
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: truefoundry-guardrails
Source: https://github.com/truefoundry/tfy-gateway-skills/tree/main/skills/guardrails
Command: npx skills add https://github.com/truefoundry/tfy-gateway-skills --skill truefoundry-guardrails

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Guardrails provide content safety controls for TrueFoundry AI Gateway, including PII filtering, moderation, prompt-injection detection, and custom rule engines to protect endpoints and MCP tool calls.

Core Features & Use Cases

  • Configure guardrail providers and gateway guardrails to enforce content safety across LLM inputs, outputs, and MCP tools.
  • Compose rules that apply PII redaction, moderation, and prompt-injection checks to specific models, users, or tools.
  • Quick scenario: add a PII guardrail so all tool invocations containing sensitive data get redacted before sending to downstream services.

Quick Start

Create a guardrail provider config and attach a gateway guardrails config to enforce safety across the gateway.

Frequently Asked Questions about truefoundry-guardrails

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure content safety guardrails for an AI gateway?▼

To configure content safety guardrails, you register guardrail providers, create guardrail rules, and attach gateway guardrails configs to enforce PII filtering, moderation, and prompt-injection detection across models and tools.

Can I redact PII from tool invocations before sending data to downstream services?▼

Yes, you can apply a PII guardrail rule so all tool invocations containing sensitive data get redacted automatically before sending to downstream services via the TrueFoundry AI Gateway.

What types of content moderation rules can I apply to LLM inputs and outputs?▼

You can compose rules for PII redaction, content moderation, prompt-injection detection, secret detection, and custom validations, applying them to specific models, users, or MCP tools.

How do I attach guardrail rules to specific MCP configurations?▼

You attach guardrail rules to MCP configurations by integrating with the tfy-api.sh or REST API to create and update guardrail config groups and gateway guardrails configs.

Does TrueFoundry guardrails work with custom validation rule engines?▼

Yes, the guardrails system supports custom rule engines, allowing you to define and enforce custom validations alongside built-in PII filtering and prompt-injection detection across your endpoints.

What are the limitations of applying content moderation rules to LLM traffic?▼

Configuring content moderation requires setting up guardrail config groups and integrating with tfy-api.sh or REST API for create/update operations, meaning rule changes depend on proper API integration and gateway attachment.

Related Skills

Explore More Legal & Compliance Skills→
passionseedpassionseed
2

guardrails

Configure and enforce content safety guardrails for TrueFoundry AI Gateway.

Official
Advanced
nexus-labs-automationnexus-labs-automation
7

guardrails-safety

Instrument AI agent inputs and outputs with safety and policy guardrails.

Official
Advanced
truefoundrytruefoundry
13

guardrails

Configure content safety guardrails for AI Gateway endpoints.

Official
Advanced
NVIDIA-NeMoNVIDIA-NeMo
58

guardrails-plugin

Implements input/output guardrailing for chat-completions traffic in NeMo Inference Gateway.

Official
Advanced