Local LLM Guard for Ollama / llama.cpp

io.github.AIops-tools/ai-guardian

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

View repository →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "ai-guardian": {
      "command": "uvx",
      "args": [
        "ai-guardian-aiops"
      ]
    }
  }
}

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
AI & ML
Version
0.14.1
Registry
active
Published
11/8/2026

More AI & ML servers

Browse all AI & ML →

Inference AIops

AIops-tools

Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.

AI & MLAdded 1 week ago

x402 Agent Tollbooth

ak10082247-max

On-chain DeFi smart contract auditor, arbitrage scanner, and agent tollbooth via x402 on Base.

AI & MLAdded 3 weeks ago

AI Firewall MCP

Akhilucky

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

AI & MLAdded 5 months ago

AIMarket — live agent marketplace

alexar76

Search and invoke real AI capabilities on modelmarket.dev. Free trial, then a prepaid key.

AI & MLAdded 1 month ago

NeuralBrain

alexcurpan-cloud

NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments

AI & MLAdded 4 months ago

Mantis

Alfred768

Cross-venue prediction market routing for AI agents with arbitrage, quotes, history, and signals.

AI & MLAdded 4 months ago

Add the badge to your site

Show visitors that Local LLM Guard for Ollama / llama.cpp is listed here — it’s also the link we check for a free listing.

Local LLM Guard for Ollama / llama.cpp — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-aiops-tools-ai-guardian?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Local LLM Guard for Ollama / llama.cpp — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Local LLM Guard for Ollama / llama.cpp — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-aiops-tools-ai-guardian?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.