- Conduid
- Marketplace
- #ai-safety
MCP servers tagged ai-safety
56 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.
Template Repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
Deterministic Agent Control Protocol
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible…
mcp-guardian
MCP security scanner - detect prompt injection in tool descriptions
Agentidentityprotocol
Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.
agentos-server
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Chimera-Protocol/csl-core
Deterministic safety layer for AI agents. Z3-verified policy enforcement.
knowledgepa3/gia-mcp-server
MCP proxy for GIA Governance — connects Claude Desktop and Claude Code to the hosted GIA governance engine
Agentgate
API gateway for AI agents to access your personal data with human-in-the-loop write approval.
Qwed MCP
MCP Server for QWED Verification - Use QWED verification tools in Claude Desktop, VS Code, and any MCP client
Vibe Check MCP
Stop AI coding disasters before they cost you weeks. Real-time anti-pattern detection for vibe coders who love AI tools but need a safety net to avoid expensive overengineering tr…
Agentmesh MCP Proxy
Public Preview — Security proxy for MCP servers: The Firewall for Model Context Protocol
Read No Evil MCP
A secure email gateway MCP server that protects AI agents from prompt injection attacks hidden in emails.
sim-xia/blind-auditor
MCP tool for improving model coding quality by mandatory self-audition
Safeclaw
Safe-by-default AI agent. Gates every action through Authensor before it executes.
Cordum
Cordum (cordum.io) is a platform-only control plane for autonomous AI Agents and external workers. It uses NATS for the bus, Redis for state and payload pointers, and CAP v2 wire…
Agentic AI
Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
Reins
Runtime security for OpenClaw agents. Scan, fix, monitor.
Www Project Agent Memory Guard
OWASP Foundation web repository
Agent Safe Pipeline
Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), veri…
Node9 Proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
Pattern8
🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8
AI Driven Development
Practices, protocols, and skills for AI-driven software development. 18 skills + 1 Bash safety hook for Claude Code, Codex CLI, OpenCode, Cursor, Gemini CLI, Antigravity, and any…
Twin Github
Deterministic GitHub-shaped twin for agent testing — REST + MCP, SQLite-backed state.
Intercept
Control every MCP tool call your agent makes. Set budgets, approvals, and hard limits across MCP servers. So your agent can do its job without breaking things. Open Source
webcite-server
WebCite MCP Server - Fact-check AI claims against authoritative sources. Works with any MCP-compatible agent or tool.
Avakill
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Ant…
Hardened Skills
200 AI agent skills, hardened with targeted behavioral guardrails. Free drop-in replacements.
IgorGanapolsky/ThumbGate
action gates via PreToolUse hooks. Install: `npx thumbgate`.
MCTS
MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers, auditable risk scores, and JSON, SARIF…
Trustabl
Static analyzer for agent reliability.
LLM Differential Privacy Gateway
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record c…
mcpwall
Deterministic security proxy for MCP tool calls. Blocks dangerous requests, redacts secrets from responses, catches prompt injection. No AI, no cloud, pure rules.
Phantom Secrets
MCP server for Phantom Secrets — lets AI coding tools manage API keys safely without ever seeing real values. 10 tools for Claude Code, Cursor, Windsurf, and Codex.
Quality Gate
Quality gate for MCP servers — compliance, security, and efficiency testing
Reagent
Governance layer for Claude Code — policy enforcement, hook-based safety gates, and audit logging for AI-assisted projects
Rea
Agentic governance layer for Claude Code — policy enforcement, hook-based safety gates, audit logging, and Codex-integrated adversarial review for AI-assisted projects
Altais
Modular, open-source MCP server providing comprehensive security analysis for AI coding agents.
Free AI Ops
Free MCP server for developers adding human review gates, prompt risk checks, FAQ review, and CRM note safety to AI tools.
Prism Verify
prism-verify — runtime LLM verifier (family-different, reasoning-stripped, multi-lens, signed Ed25519 receipts). Zero-prerequisite npx install via a verified binary launcher.
Metago Lifeform
MetaGO Agent Harness（智能体运行时控制层套件 · 驭智层）— 智能体运行时控制层，让智能体从工具升级为守规矩、会进化、可追溯、能闭环的生命体。39 技能 · 53 MCP tools · 8 公理 · Engine V2（KMWI 四层记忆 + 元进化五阶段 + 技能智能生成）· 决策锁四道关卡 · 全链路溯源。支持 7 大 AI 编程…
Governance
MCP Governance Server — wraps any MCP server with MAREF governance guardrails. Intercepts file writes and command execution to enforce policies via MAREF sidecar.
Border Patrol
A policy-enforcing MCP gateway: one MCP server that proxies all your others and blocks dangerous tool calls
Forge Plugin
Forge Plugin: Zero-dependency governance for Claude Code. 21 commands, 22 agents, 29 skills.
Map1
Deterministic identity for structured data
Sint Protocol
Open protocol and reference stack for governing AI agent actions in physical and safety-critical systems
Agent Guardrails
Merge gates and safety checks for AI coding agents. Works with Claude Code, Cursor, Windsurf, Codex via MCP. Detect scope violations, missing tests, and risks before merge.
sint-ai/sint-protocol
risk audits.
sidclawhq/mcp-guard
no SDK needed.
cuttalo/depscope
mcp`.