MCP.so
ログイン
タグ

21 #ai-safety MCP Servers & Clients

Every MCP server and client below is tagged #ai-safety — install one to give Claude, Cursor, VS Code, or any other MCP-compatible client access to ai-safety tools.

すべて

Rust Docs MCP Server

Govcraft

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

昨年 に追加

Thumbgate

IgorGanapolsky

Agent governance for ThumbGate: 👍/👎 become Pre-Action Checks that block repeat mistakes before code, money, or customer systems change.

3 か月前 に追加

Enkrypt AI MCP Server

enkryptai

昨年 に追加
FP

Five Persona Engine

kiro0x

LLM persona consistency engine — enforce JSON personality and style constraints across interactions. Prevents persona drift with 160,000 deductively-derived behavioral rules.

先月 に追加

nexus-mcp — jpi-guard & PII Guard

nexus-api-lab

Japanese LLM security APIs — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free to start, no credit card required.

3 か月前 に追加
W

Wisegit

Sandip124

MCP server that extracts decision intent from git history and protects intentional code from AI modification.

4 か月前 に追加
CC

Claude Code Guardian

phuongrealmax

AI-Safe Code Analysis with 113+ MCP tools - guard, memory, workflow, testing, latent chain

7 か月前 に追加
GP

Glin Profanity Mcp

GLINCKER

Content moderation and profanity detection MCP server with 19 tools, 24 language support, leetspeak/Unicode obfuscation detection, context-aware analysis, batch processing, and user tracking for AI-powered content safety.

5 か月前 に追加

Safer Agentic AI MCP

NellInc

SaferAgenticAI MCP brings the Safer Agentic AI safety framework to coding assistants over the Model Context Protocol.

7 日前 に追加

Safer Agentic Ai Framework

NellInc

7 日前 に追加
TG

Trust Gate MCP — First post-quantum MCP server. Policy-gated AI agent decisions with hybrid Ed25519 + ML-DSA-65 (NIST FIPS 204) cryptographic receipts. No Receipt. No Trust.

Cyber-Warrior-Network

The first production MCP server with NIST FIPS 204 post-quantum receipts. Every AI agent tool call is policy-gated, hybrid-signed (Ed25519 + ML-DSA-65), and forensically provable — offline, forever. Fail-closed architecture: if the Trust Gate backend is unreachable, every decisio

2 か月前 に追加
B—

BLACK_WALL — Pre-action risk gate for AI agents

bluetieroperations-create

A single `forecast` tool your agent calls before any irreversible action (send money, run SQL, delete data, post content). Returns a risk score (0–100), a reversibility class, named red flags from 28 failure modes, and a gate: proceed / confirm / human-required.

2 か月前 に追加

Npmguard

AyoubTadlaoui

Pre-install risk gate for npm packages. Stops AI coding agents from running malicious or typosquatted packages before lifecycle scripts run.

2 か月前 に追加

Couchloop EQ

wisenbergg

CouchLoop EQ is an MCP (Model Context Protocol) server that provides behavioral governance for LLMs. It monitors AI responses for hallucination, inconsistency, tone drift, and unsafe reasoning patterns, while also managing stateful sessions and guided journeys that remember where

5 か月前 に追加
OM

Oathe Mcp

oathe-ai

MCP server for https://oathe.ai security audits. Runtime behavioral analysis and security scanner for AI systems. Check trust scores before installing MCP servers, plugins, or AI agent skills.

5 か月前 に追加

🧭 Vibe Check MCP

kesslerio

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 traps.

昨年 に追加

Fidensa MCP Server

fidensa

Independent AI certification authority. Check trust scores, search certified capabilities, compare side-by-side, verify signed artifacts, and report runtime experience for MCP servers, skills, rules files, hooks, sub-agents, and plugins. 50 certifications live.

3 か月前 に追加
SA

S2T Accelerators

S2TConsulting

36 enterprise-grade MCP tools for AWS infrastructure, security compliance, AI workflows, agent governance, and operational resilience. Includes IAM policy validation with security scoring, MFA compliance auditing, CloudFormation/SAM template generation, DynamoDB single-table desi

5 か月前 に追加
AN

Aaaa Nexus

atomadictech

Formally verified AI safety APIs for autonomous agents. 75+ endpoints, x402 USDC micropayments, MCP server, A2A protocol. No signup required.

3 か月前 に追加
A

Actionproof

Burakfenerci5

Gives AI agents verifiable, tamper-evident receipts for their actions — attest_action signs a cryptographic receipt for what the agent did (email sent, payment made, form filed), verify_receipt checks it offline, get_identity returns the agent's did:key. Sign locally, verify anyw

8 日前 に追加

Kultur.dev — Cultural Intelligence Layer

Global-InTech-AS

Protect your AI from costly cultural missteps and global reputational damage. The world's first Cultural Intelligence API and MCP Server with six powerful endpoints — text analysis, content rewriting, culturally-native generation, knowledge queries, image analysis, and video anal

3 か月前 に追加

Frequently asked questions

What is a #ai-safety MCP server?

An MCP server tagged #ai-safety implements the Model Context Protocol so AI assistants like Claude, Cursor, and VS Code can access ai-safety-related tools, data, or APIs.

How many #ai-safety MCP servers and clients are there?

mcp.so currently lists 21 MCP servers and clients tagged #ai-safety.

How do I install a #ai-safety MCP server?

Open any server below and copy its install snippet into Claude Desktop, Cursor, VS Code, or another MCP client's configuration — remote servers need no separate download.