# llm-guard-gateway

> llm-guard-gateway — shreyac962-llm-guard-gateway. Use this tool when you need to secure and govern large language model (LLM) traffic, enforcing data protection and usage policies. It solves problems such as prompt injection, sensitive data exposure, and excessive token usage by blocking, redacting, and caching requests. By routing model calls through this gateway, AI agents can ensure compliant and efficient interactions with LLM providers.

Canonical page: https://skillsregistry.net/skills/shreyac962-llm-guard-gateway  
JSON: https://api.skillsregistry.net/v1/skills/shreyac962-llm-guard-gateway

## Description

Provides a governance gateway for LLM and agent traffic via MCP, blocking prompt injection, redacting PII, enforcing per-tenant token budgets, and caching repeat questions semantically. Enables AI agents to route model calls through the same guardrails instead of calling providers directly.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/k4x9g8fzgk)
- **Repository:** <https://github.com/ShreyAC962/llm-guard-gateway>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shreyac962-llm-guard-gateway"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shreyac962-llm-guard-gateway` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shreyac962-llm-guard-gateway/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt