- 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.
Positionguard MCP
MCP server for PositionGuard: area-level presence for AI assistants, read-only, no coordinates. Answers only what a member has chosen to share, and says 'unknown' otherwise.
L-Jovi/keyhole
checked edits and recovery. No shell or public port.
Smallprint Tools
Small Print's open tools: the disclosure lab, and soon the command, the MCP server and the plugin
Causallayer Verifier
🔍 Independent zero-dependency verifier for CausalLayer AI-liability certificates. Verify without trusting the issuer.
Agent Passport
Open standard for verifiable AI agent identity and authority. One signed JSON file at /.well-known/agent-passport.json, keyed in DNS. Verifier, spend caps, signed receipts, CLI an…
Witness
🔐 Cryptographic audit trails for AI decisions — hash chains, Merkle trees, RFC 3161 timestamps, compliance presets for HIPAA/GDPR/SOC2
Mcd Guard
麦麦护栏：把麦当劳账号交给 AI 之前，先装个刹车。本地 MCP 安全层：下单等写操作需本机确认、消费上限、只读模式、审计日志，Token 只在本机。Human-in-the-loop guard proxy for McDonald's China MCP.
Agentrelay
Supervise an AI coding agent (Claude Code / Codex / ACP) overnight and keep control: block forbidden tool calls before they run, gate 'done' on real tests, checkpoint work to git,…
Warden
Drop-in security proxy for MCP — policy, tamper-evident audit, human approval, prompt-injection & secret-exfil defense. One line of config, zero code.
Airlock
Nothing reaches production without passing through the airlock. A change-control console where every irreversible production change is proven on a shadow copy in a sandbox before…
Elodea
Inline policy enforcement proxy for AI agents: OPA policies on MCP tool calls, human approval for risky actions, and a hash-chained audit ledger.
AgentGuard
Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.
SAGE
Official implementation of SAGE: A deployment-oriented evaluation framework for LLM-based autonomous agents (IEEE Transactions on Artificial Intelligence).
Agentguard
Safety and audit framework for autonomous AI agents — policy enforcement, append-only audit logs, MCP integration
CHIMERA
Chained Harm & Injection Measurement for Evaluating Risks in Agents — a red-team research framework that tests hosted models, agentic apps, RAG pipelines, MCP servers, AI coding a…
Agentgate
Policy, human approval, and a tamper-evident audit trail for AI agent tool calls
Policy Reasoning Bench
Hand-built benchmark of regulatory and cost-benefit analysis tasks with expert rubrics — philosophy, economics, law/policy.
Agent Gate
Governed AI agents with an MCP server: least-privilege tool grants, human approval for writes, PII redaction, audit log, rollback, and safety evals in CI.
Doctor
Scan, Score, Install MCP Servers with confidence. The missing toolkit for the MCP ecosystem.
Scanner
MCP Scanner — 12 security checks for MCP server configurations. SARIF output.
Verify
ESLint for AI tools: Automated LLM-readiness, schema contract, and safety linter for Model Context Protocol (MCP) servers.
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`.
wei9072/aegis
emits BLOCK / WARN / PASS verdicts, never coaches the agent.
Knox
Security enforcement plugin for Claude Code. Blocks dangerous commands, audits every tool call, detects prompt injection.
Ammp MCP
Reference implementation of AMMP (Agentic Mentor-Mentee Protocol, draft-arturo-ammp-01), Mentoring track, on FastMCP. Multi-mentor + multi-mentee, LLM-synthesised AskMentor with c…
Atomicapis MCP Server
MCP server with 17 production-grade micro-API tools for AI assistants
Warrant
Verifiable constraint enforcement for AI agents - signed warrants, Merkle constraint commitments, tamper-evident audit logs, and collusion-aware multi-agent auditing. Rust core +…
ClawCrate
Policy + evidence for everything your AI agent executes. 🦀 Kernel-native sandbox for agent commands & MCP servers — Landlock+seccomp (Linux), Seatbelt (macOS). Tamper-evident, off…
Fronesis-Labs/dcl-webhook
call via x402 (USDC on Base), from $0.01. `mcp.fronesislabs.com/mcp`
Hvtracker
AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance d…
MCPBoundary
A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can…
DontPanic
Keep AI coding agents honest. DontPanic is a vendor-neutral meta-harness that makes agents work to a locked plan, has a second model check the work, and asks a human before risky…
152fz Anonymizer
Автоматическое обезличивание персональных данных (ПД) по 152-ФЗ. Готовый MCP-сервер и API для безопасной работы ИИ-агентов, n8n и LLM.
Pinnedai
Permanent guardrails for AI-coded apps
Agent Prod
Production AI agent quality gate and risk control framework for LLMOps, agent evaluation, regression detection, gray release, audit, and observability
Ghostimport
👻 Detects ghost imports — npm packages that don't exist, hallucinated by AI coding tools like Cursor, Copilot, and Claude
AI Failure Observatory
Behavioral safety, vulnerability probing, and product-risk auditing platform & MCP server for Generative AI & Large Language Models.
Council MCP
MCP server that gives Claude a review council - other LLMs fact-check responses before you see them
Neuroverseos Governance
Deterministic governance engine for AI agents. Enforce rules defined in .md governance files across AI systems.
Evopilot
Local-first workflow compiler that turns repeated AI-agent work into evidence-backed, quality-checked Skills.
Vigilance
A security minded , realtime AI Intent Observability MCP providing intent tagging and visual mirroring of AI attention to see what context the AI is looking at. Made for visual an…
Stress Test
Red team toolkit for stress-testing MCP security scanners — find detection gaps before attackers do
Smartmonetize AI Powered Revenue Growth Engine
Revenue triage CLI + public fit-check issue for products with attention but no paid conversion.
Frame Pulse MCP
AI-native MCP server for creative workstation telemetry—let Claude/Hermes monitor CPU/thermal, throttle background apps, alert Discord/Telegram. Python + Streamlit.