- 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.
Mcpharden
MCP server hardening linter — capability declarations, transport, tool descriptions
Kalairos
Durable, private, time-aware memory engine for long-running AI agents
Github Tool Eval
FastMCP GitHub server with confirm-gated destructive tools and a 30-case evaluation harness scoring tool selection, argument accuracy, and confirmation safety.
QMesha
MCP-native agent middleware with governance enforced in code: spending limits that refuse before execution, auditable decision provenance, and local-first Markdown memory.
Dcl Skills
Security & compliance skills for AI agents (jailbreak defense, PII/secret redaction, hallucination checks) with a DeFi-specialized suite — free instruction-only mode or paid on-ch…
Ctrlrun
The execution safety layer for AI agents.
Csc Agent Guard V1
Deterministic pre-execution safety gate for AI agents: verify tool calls against trusted evidence, policies, and WorldState before side effects.
Aicard
Auto-generated NIST AI RMF / EU AI Act Annex IV model & system cards
Tool Card Spec
MCP Tool Cards v0.1 draft. Per-tool disclosure documents for Model Context Protocol servers: input/output schema, side-effect classification, tested-LLM matrix, latency, cost, aud…
Seshat App
Local MCP proxy that governs what AI agents do on your machine. Policy enforcement, audit receipts, hash-chained provenance.
Tenth Man MCP
Adversarial review system for autonomous AI coding agents. 3 contrarian agents challenge every critical change before execution.
Vaporcheck
Stops AI coding assistants from using packages, files, and functions that don't exist. A safety net against hallucinated and slop-squatted names.
Remit Mind
Autonomous AI-Powered Remittance Copilot & MCP Server
Principia Robotica
World-first unified MCP gateway + Control Barrier Function (CBF-QP) safety engine for agentic robotics.
Awesome Agentic Ecosystem
A curated, auto-updating collection of the most useful AI Agents, MCP Servers, Agent Skills, AI Plugins, and Frameworks.
Multi Judge Consensus
Cross-vendor multi-model review committee that gates AI/agent-generated content before it ships — consensus-based hallucination defense. Zero dependencies, local-first CLI, MCP se…
Sunglasses
Sunglasses for AI agents. Protection layer + neighborhood watch.
Agent Sudo
Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.
Execution Proofs
Runtime artifact existence & freshness verification for AI agent completion claims — a lightweight, zero-LLM MCP gate that source-binds 'done' claims to real files. MIT.
Npmguard
npmguard secure AI agents auto-edits flows by screening every npm package for known-malicious code and typosquats before anything runs, in Claude Code, Cursor and Codex over MCP o…
Agentbreaker
AI security testing engine for surfacing prompt leaks, bypasses, and unsafe agent behavior.
SkillGate
Pre-merge and pre-install trust checks for AI-agent skills and MCP configurations. Scan capabilities, detect risky changes, and block unapproved agent behavior in CI.
Project Guardian
AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy bo…
Daimon
Give any AI eyes, hands, and a face on your desktop — a local, open MCP daemon for macOS and Windows, with a safety ceiling Daimon enforces itself.
Agentgate Governed Writefile Demo
Smallest outsider-readable proof path through AgentGate + MCP Firewall: governed write_file, independent on-disk verification, and inspectable audit artifacts.
ABSuite Core
ABSuite is the trust layer for autonomous systems, providing evidence, verification, governance, and accountability for intelligent systems.
Dogma
Values ingrained, sovereignty sustained — governance framework for endogenous AI workflows
Aletheia Paper
Aletheia: A Taxonomy and Empirical Evaluation of Behavioral Failure Patterns in Large Language Models
Genefoundry
A modular registry for trustworthy, evidence-based genomic analysis powered by Model Context Protocols (MCPs). Bridging AI and clinical genomics with traceable, validated data ret…
Aluminum Os
BULLSHIT GROK · BULLSHIT CLAUDE — Quarantined by repository owner; excluded from the active Continuum OS workspace.
Seatbelt
Seatbelt for MCP tools: local policy checks, audit logs, and a dashboard for safer AI tool use.
Cys Prompt Suite
中文人像、动漫与 MiniMax H3 提示词 MCP：可复现词库采样、严格参数校验、风险短语复检，以及默认隔离第三方 IP 的商用友好边界。
Qedra
A runtime gate for coding agents: an MCP server that blocks the tool calls that wreck a repo (force-push main, rm -rf, secret exfil, CI wipe) and lets real work through. Machine-c…
Ghl MCP Scoped
Least-privilege policy wrapper for any GoHighLevel MCP server. Declare which tools an AI agent may call and under what argument conditions; everything else is refused and logged.…
Chiron Agent
Autonomous, self-improving AI agent platform for Claude Code — safe capability & skill acquisition, MCP/tool discovery, sandboxed policy gates, and token-efficient learning.
Ephorate AI Governance And Monitoring
Open-source control plane for AI agent security & governance — runtime policy enforcement, tamper-evident audit, prompt-injection detection (SIEM/EDR) and compliance mapping (NIST…
World999 Labs Proof Layer
Proof Layer is a cryptographic governance layer for AI agents. Before an agent action executes — a database write, API call or workflow step — Proof Layer evaluates it against pol…
Agent Receipt
MCP middleware that creates cryptographic receipts for every real tool call — ghost actions leave no receipt
Cross Provider Egress Guard
Destination-aware, default-deny egress control for AI coding agents, at the tool-dispatch layer across Claude Code and Codex from one shared policy.
Project Sentinel
npm audit for AI agents — scan, certify, and enforce trust for MCP servers. Security scanner, trust certificates, YAML-configured gateway.
Pfc Connector Gateway Proof
PFC delegation chain governing MCP connector calls, pre-effect gating, scope containment, mid-run revocation that fails closed, signed Ed25519 receipts. Reference implementation,…
Stage0 Authorization
MCP server demonstrating server-side authorization with Stage0 runtime policy validation
Sagaz
Undo for AI agents — an MCP proxy with a hash-chained effect ledger, reversibility classification, policy gates and preview.
Medsguard Agent
An LLM-driven medication-logging agent with a deterministic safety spine.
Agentcloud
Governed persistent AI workers with default-deny authority, human approvals, dry-runs, and an authenticated MCP.
Warder
A policy gate for MCP tool calls. Blocks destructive AI agent actions before they run — as the subprocess your AI client launches, where network gateways can't see.
Loomdb
An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a p…
Turnstile
Scan any MCP server: a token-cost + metadata-safety report card at the tools/list boundary. Deterministic, i18n-honest concealment detection. Python + TypeScript.
Agent Rewind
Agent Rewind: flight recorder + undo button for AI agents (MCP interception proxy — journal, snapshots, policy gate, kill switch, rewind)
Jv Watchtower MCP
Read-only MCP operations console over a 24/7 algorithmic trading fleet (sanitized portfolio extract). Sanitization is enforced in the data layer, so the strategy never reaches the…