Local LLM Guard for Ollama / llama.cpp
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Open the source (opens github.com) https://github.com/aiops-tools/ai-guardian
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.AIops-tools.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
ai-guardian-aiops@0.14.1
From the server's entry in the official MCP Registry
Related
-
CoWork-OS
MCP serversRent the model. Own everything else. Free, open-source AI app for real work.
git clone https://github.com/CoWork-OS/CoWork-OS.git -
phi-guard-mcp
MCP serversLocal-first PHI detection for source code, LLM prompts, logs, and analytics
phi-guard-mcp@0.2.0 -
spring-ai-privacy-guardrails
MCP serversPrivacy guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and optional Spring Security tool authorization. Supports Presidio and JVM-local OpenNLP.
git clone https://github.com/ultramancode/spring-ai-privacy-guardrails.git -
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.git -
www-project-agent-memory-guard
MCP serversRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
git clone https://github.com/OWASP/www-project-agent-memory-guard.git -
guard
MCP serversLocal-first architecture guardrails and project context for JS/TS AI coding agents.
@codapult/guard@0.14.1