- Conduid
- Marketplace
- #safety
MCP servers tagged safety
34 live MCP servers tagged "safety", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with safety.
Safetext
Fast profanity word, curse word, swear word, bad word filtering tool for English, Spanish, Chinese, Turkish and more.
Genpark Hallucination Fact Grounding Checker Skill
GenPark AI Agent Skill - Sentence-level fact grounding and hallucination verification engine comparing LLM claims against retrieved source evidence.
Boucle Framework
Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.
Sentinel AI
Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript…
Codex Web Gpt Automation
Guarded, recoverable web ChatGPT automation for local Codex projects on Windows and macOS
Toxmcp
Umbrella repo for the ToxMCP Suite (docs, links, quickstart).
Cpex
A policy enforcement runtime for AI agents
Acp Find
MCP server for searching the Virtuals Protocol ACP marketplace + Degen Arena + portfolio risk scoring + cross-portfolio composition. Exposes 39 tools — v0.12.1 adds a marketplace…
Rivet
Rivet — SDLC traceability, validation, and MCP server for safety-critical systems (ISO 26262, DO-178C, ASPICE, STPA)
VibeGuard
Stop AI-generated vibes, catch bugs, and scan sites locally with zero-dependency pre-commit guard and AI Studio.
Schema MCP Core
Ядро для MCP-серверов из каталога эндпоинтов: поиск методов, классы доступа, HTTP-клиент, хранилище ключей | Core for schema-driven MCP servers: method search, access classes, HTT…
Agentblackbox
AAPP: Flight Recorder for AI Agent Tool Actions. Prove what an AI agent was allowed to do, what tool it requested, what policy decided, and whether the evidence was changed later.
Safegen
Generate safer MCP servers from OpenAPI specs with pruning, auth templates, and tool scoring.
Steward AI
Healthcare AI stewardship prototype using FHIR context, MCP tools, and A2A/ADK agent concepts. Research/hackathon framing.
Momo Tools
Local-first capability router and safety gate for AI agent tools
Guardrail
Scan AI-generated code for security, performance, and code quality issues before they ship
Agentgate
Production-grade permissions, hooks, and tool safety for AI agents. Works with any LLM provider.
Acgs Lite
Constitutional governance infrastructure for AI agents — the missing safety layer between your LLM and production
alexar76/aimarket-plugins
packager`.
Tool Card Summary
Fleet-analyze a directory of MCP Tool Cards. Counts by side-effect class, PII/secrets exposure, reversibility, human-approval-required; surfaces approval gaps (destructive tools m…
Agentic Refund Guardrail
Safe refund policy layer for AI agents — Python + TypeScript. Same behavior, shared tests.
Ros2 Agent Workflow
Safe Agent-to-ROS2 MCP framework: FastMCP, fail-closed SafetyGateway, Gazebo TurtleBot3 Burger case, 505 tests, verifiable evidence
Biz Guard
Deterministic business-change safety gate for coding agents — evidence-backed BLOCK/ALLOW decisions
Postcog
Action-safety gate and recoverability engine. Know before you go. (Companion repo — architecture and interface only. Source lives in the private engine.)
Zionfhe MCP Server Test
mcp server based on the new homomorphic encryption technology "ZionFHE"
Agent Ebpf
Zero-Code, Zero-Overhead Kernel Firewall for AI Workflows & LLM Agents (eBPF / MCP)
Cliguard
Experimental local-first guardrails for human and AI-generated CLI actions.
Autonomous Intelligence
Transaction-safe local MCP execution for AI agents
Terrabase
LLM-assisted, safety-gated Postgres migrations exposed as an MCP server. The LLM proposes, the rules decide.
Tool Card Diff
Diff two MCP Tool Card documents. Classify safety transitions (side-effect class escalation, reversible flipped to false, rate-limit removed, PII / secrets exposure escalation, hu…
Opslens MCP
Multi-agent industrial RCA with visible MCP safety gateway. Built on Anthropic Model Context Protocol.
Tool Safety Lab
Public-safe MCP-style tool safety lab with permission gates, approval boundaries, schemas, audit logs, and CI tests.
Mobile Agent Guardian
Safety infrastructure for AI agents that control real phones. Observe → classify → gate → verify → record → anchor.
VibeGuard
No description published.