InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.

    Indexed GitHub, e2sy 102 ★MITUpdated today

    git clone https://github.com/e2sy/jailbreak-archives.git
  2. On the occasion of national safety week 2026 write a safety script which engage the employee and peoples create awareness on safety by following safety guidelines in steel industry

    Indexed prompts.chat (CC0 prompt collection), marrigangu@gmail.com CC0-1.0

  3. Deterministic pre-execution safety certification for autonomous AI agents.

    Stale Official MCP Registry, io.github.tb8412 Updated 8 months ago 1 note

    qae-safety@0.1.2
  4. NHTSA Vehicle Safety

    MCP servers

    Vehicle safety recalls, complaints, and crash data from NHTSA

    Stale Official MCP Registry, com.olyport Updated 7 months ago 1 note

  5. swiss-food-safety-mcp

    MCP servers

    BLV open data for food safety and veterinary inspections

    Stale Official MCP Registry, io.github.malkreide Updated 50 days ago 1 note

    swiss-food-safety-mcp@1.2.0
  6. Tracekit

    Agents & frameworks

    Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

    Indexed GitHub, Cygnux-Labs 726 ★MITUpdated yesterday

    git clone https://github.com/Cygnux-Labs/Tracekit.git
  7. UK product safety alerts and recalls from the Office for Product Safety and Standards

    Stale Official MCP Registry, uk.co.reliness Updated 12 days ago 1 note

  8. CyberClaw

    Agents & frameworks

    👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

    Stale GitHub, ttguy0707 336 ★MITUpdated 2 months ago

    git clone https://github.com/ttguy0707/CyberClaw.git
  9. Doberman-Core

    Agents & frameworks

    Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

    Indexed GitHub, DobermanCore 243 ★Apache-2.0Updated yesterday

    git clone https://github.com/DobermanCore/Doberman-Core.git
  10. Optometry Ai Safety MCP Server by MEOK AI Labs

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 2 months ago 1 note

    optometry-ai-safety-mcp@1.0.10
  11. patient-safety-ai-mcp

    MCP servers

    Patient Safety Ai MCP Server by MEOK AI Labs

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 2 months ago 1 note

    patient-safety-ai-mcp@1.0.12
  12. Premium agentic endpoint for cobot-safety-zone-mcp.

    Stale Official MCP Registry, io.github.Evozim Updated 3 months ago 1 note

  13. huqan

    MCP servers

    Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.

    Stale GitHub, ali-ulu 30 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/ali-ulu/huqan.git
  14. All official Claude system prompts in one open-source repo from Claude Fable 5.2 to Claude Haiku 3 23 models from Anthropic's release notes, plus original analysis, tool schemas, and AI-safety research.

    Indexed GitHub, KalarisLabs 230 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/KalarisLabs/claude-systems-prompts.git
  15. Git branch name safety, name discarded

    Stale Official MCP Registry, io.github.sadri-dridi Updated 2 months ago 1 note

  16. Git tag name safety, name discarded

    Stale Official MCP Registry, io.github.sadri-dridi Updated 2 months ago 1 note

  17. Git tag name safety, name discarded

    Stale Official MCP Registry, io.github.sadri-dridi Updated 2 months ago 1 note

  18. x402-payment-safety

    MCP servers

    Authorize x402 payments before signing with request-bound, signed safety decisions.

    Stale Official MCP Registry, io.github.AgentTanuki Updated 6 days ago 1 note

  19. Premium agentic endpoint for ai-safety-incident-logger-mcp.

    Stale Official MCP Registry, io.github.Evozim Updated 3 months ago 1 note

  20. OpenFDA Safety Data

    MCP servers

    Search FDA safety data: drug adverse events, recalls, and device events.

    Stale Official MCP Registry, io.github.Taru0208 Updated 8 months ago 1 note

  21. opencompass

    Datasets & benchmarks

    OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.

    Indexed GitHub, open-compass 7,596 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/open-compass/opencompass.git
  22. uk-food-safety

    MCP servers

    UK food safety and traceability — direct sales, labelling, raw milk, HACCP

    Stale Official MCP Registry, io.github.Ansvar-Systems Updated 7 months ago 1 note

  23. onchain-safety-mcp

    MCP servers

    Token-safety for AI agents: rug/honeypot verdict + score across PulseChain, Monad, Base & BSC

    Stale Official MCP Registry, io.github.aitools420 Updated 4 months ago 2 notes

    @wickpics/onchain-safety-mcp@0.2.0
  24. food-safety

    MCP servers

    Food additive safety: JECFA, EFSA, ADI, halal/kosher/vegan. 6K+ additives. Free.

    Stale Official MCP Registry, io.github.rootsbymenda Updated 5 months ago 1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.