Best Safety AI Skills & MCP Servers

BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).

Search the PubChem chemical database for compounds, properties, safety data, bioactivity, cross-references, and entity summaries via MCP. STDIO or Streamable HTTP.

Agentic HubSpot CLI + MCP server. Covers ~all documented public endpoints (1180 across 55+ command domains). Reachability is tier/scope/auth-model gated — UI-only surfaces and deprecated APIs excluded. Enterprise safety rails, self-hosted.

ThumbGate self-improving agent governance: thumbs-up/down turns every mistake into a prevention rule and blocks repeat patterns. 36 pre-action checks, budget enforcement, and self-protection for Claude Code, Cursor, Codex, Gemini CLI, and Amp.

Query FDA data on drugs, food, devices, and recalls via openFDA. STDIO or Streamable HTTP.

Cognitive browser automation that thinks like your users—and helps AI agents navigate too. Simulate real user cognition with abandonment detection, constitutional safety, chaos engineering, and UX friction discovery. Sites that pass CBrowser's cognitive t

Decode VINs, search recalls, complaints, crash ratings, and investigations via MCP. STDIO or Streamable HTTP.

Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.

MCP server for controlling Home Assistant lights and managing scenes. Lights only by design for safety.

MCP server for Tuteliq — 50 AI-powered tools for child safety, fraud detection, synthetic content forensics, identity verification, grooming, bullying, sextortion, document analysis, and content moderation. Interactive UI widgets for Claude, Cursor, and M

Lightweight pre-commit safety gate for AI agents. Answers 'is this change safe?' with PASS/WARN/BLOCK verdict in seconds. Zero setup, no database.

MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet

The agent eval standard for MCP. Score every agent output for quality, safety, and cost.

Package Intelligence MCP server for AI agents. Stops hallucinated/malicious package installs across 19 ecosystems (npm, PyPI, Cargo, Go, Maven, NuGet, RubyGems, Composer, Pub, Hex, Swift, CocoaPods, CPAN, Hackage, CRAN, Conda, Homebrew, JSR, Julia). 22 to

Solana Token Safety API & MCP Server — rug pull, honeypot, and safety analysis for AI agents

Termyte eats dangerous agent actions before they eat your codebase

Use the MCPSkills pre-install trust layer from Claude Code, Cursor, or any MCP client. Accepts GitHub repos, npm packages, Smithery URLs, and OpenClaw skills. 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence), safety scanning, OpenClaw frontmatte

MCP server with 22 tools for marketplace search, price comparison, license verification, childcare costs, estate sales, storage pricing, GSA auctions, home services, FCC lookup, and AI skill safety — TCGPlayer, Reverb, Grailed, Redfin, Poshmark, Craigslis

Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

1trip PULSE — The #1 travel planning MCP server. 21 tools, 5 resources, 6 prompts. Live flights, hotels, weather, currency, visa, safety (50+ countries), trip skeletons, validation, insights, packing, local tips, personas. 120+ city cost index. Works with

MCP server for ThoughtProof — verify AI reasoning with adversarial multi-model consensus

Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions

Typed SDK for building FocusMCP bricks — defineBrick() helper with full type safety for tools, manifests, and bus handlers.

A TypeScript library for selective context access, visibility control & safety enforcement for LLMs