#safety

type safety mcp servers with deno.

🔒 Atomic Writer MCP Server: A secure file operation service that prevents data loss through atomic transactions. Built for AI integrations, collaborative editing, and critical data management.

Mirror of

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

Mirror of

MCP server for session continuity and sandbox safety in LLM development workflows. Provides "pick up exactly where you left off" + "never break the main app" functionality.

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

🦀 Prevents outdated Rust code suggestions from AI assistants.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.

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.

About MCP to enable AI agents to guide users towards miklatim tziburim (public shelters) in Israel

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 you left off.

Deterministic MCP server that scores code risk BEFORE execution. Returns ALLOW or BLOCK with full reasoning. Same inputs → same output. Always.

Make your AI agents cheaper, faster, and more reliable. 5 products, 14 MCP tools, 1 API key. Task deduplication, cost prediction, output validation, behavioral governance, and shared failure intelligence. Anonymous demo mode — try all tools without a key. 1,000 free credits/month, no card required. https://plith.ai/.well-known/mcp/server-card.json

Quick safety screening for any Solana SPL token. Returns: risk score (0-100), risk level (LOW/MODERATE/HIGH/CRITICAL/EXTREME), human-readable summary, token name/symbol, whether authorities are renounced, trusted_authority (true when active authority belongs to a known issuer like Circle USDC or Tether), liquidity rating (DEEP/MODERATE/SHALLOW/NONE), top-10 holder concentration percentage (PDA-adjusted — only known DeFi protocol accounts excluded via whitelist), honeypot status (can_sell), token age, Token-2022 extension risks, data confidence (complete or partial), and degraded note (human-readable explanation when partial). This is a FREE lite check — for full details (individual authority addresses, top holder breakdown with addresses, wallet/PDA classification, owner program identification, LP lock status and locker identity, honeypot sell tax, field-level change detection), use the x402 paid endpoint at $0.008 USDC per request.

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.

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 analysis — covering 195 countries, all industries, every region, and 500M+ data points. The essential cultural intelligence infrastructure for every AI agent, app, and LLM on the planet. Integrate in minutes.

Local-first memory firewall and MCP server for AI agents. Audrey gives coding agents recall, memory capsules, preflight checks, reflexes, validation, tool-trace learning, contradiction handling, and SQLite/sqlite-vec storage.

Deterministic cross-branch conflict detection for AI coding agents. Scans your git repo for function signature mismatches, HTTP route conflicts, and schema breaks across branches using tree-sitter AST analysis. Catches the merge failures that CI misses because tests only run on one branch at a time.

Source trust for AI agents — evaluates URLs and domains before ingestion, returns proceed/deny decisions with scores and reason codes.

16 tools, 5 resources, 3 prompts for HACCP food safety compliance in France. Live RappelConso alerts and Alim'confiance inspection scores.