- Conduid
- Marketplace
- #ai-safety
MCP servers tagged ai-safety
464 live MCP servers tagged "ai-safety", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-safety.
Agent Cordon
Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.
Canary
Which fields of an MCP tool result actually reach the model's context, measured with benign canaries across every installed server
Safe Skills
🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.
Skillforge
The free open registry for reusable AI agent skills — search, safety-score, compose, install.
Changeguard AI
Advisory PR change-impact analyzer: deterministic rules with evidence and coverage, grounded LLM recommendations with citation validation (in progress). Python, FastAPI, PostgreSQ…
Stopcord
A containment layer for AI agents: a policy gate in front of every tool call, a tamper-evident log, and a stop switch.
Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
Agent Firewall
Lightweight, zero-dependency AI Agent runtime firewall (L7 HTTP Proxy + MCP Sandbox) in Go.
Project Infinity1
No description published.
Learn Agent Harness
No description published.
AILIS
No description published.
Trust Audit MCP
No description published.
Trust Layer MCP
No description published.
.github
No description published.