InnerVault

Library

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

Results

  1. SafePrompt

    MCP servers

    Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

    Stale Official MCP Registry, dev.safeprompt Updated 18 days ago 3 notes

    @safeprompt.dev/mcp@0.1.1
  2. PromptGuard Scan MCP

    MCP servers

    Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.

    Stale Official MCP Registry, space.promptguardscan Updated 6 months ago 1 note

  3. ascript-mcp

    MCP servers

    Control Android/iOS/Windows devices from Claude, Cursor, and other AI tools. iOS without jailbreak.

    Stale Official MCP Registry, io.github.ascript-cn Updated 6 months ago 1 note

    ascript-mcp@1.7.0
  4. Koma Gate MCP

    MCP servers

    Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

    Stale Official MCP Registry, io.github.swnotmetal Updated 3 months ago 2 notes

    koma-gate-mcp@0.1.1
  5. icme-preflight

    MCP servers

    Jailbreak-proof AI guardrails. Automated Reasoning SMT solver, not an LLM. ZK proofs included.

    Stale Official MCP Registry, io.github.wyattbenno777 Updated 7 months ago 1 note

  6. Control real, physical iPhones with AI: screen reading, human-like touch, no jailbreak.

    Stale Official MCP Registry, app.icemoon Updated 3 months ago 1 note

    icemoon-mcp@1.0.1
  7. Prompt Compass

    MCP servers

    Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

    Stale Official MCP Registry, io.github.rishabhmpc Updated 3 months ago 3 notes

    @mpcfintech/prompt-compass-mcp@1.0.1
  8. LLM Security Scanner

    MCP servers

    LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 13 days ago 1 note

  9. Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 13 days ago 1 note

  10. Check user prompts for injection/jailbreaks; your own guard learns from your labels. Works keyless.

    Indexed Official MCP Registry, com.darmousseh Updated yesterday 2 notes

  11. LLM Red-Team Scanner

    MCP servers

    LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails

    Stale Official MCP Registry, io.github.manhliemcn4euwlu-source Updated 21 days ago 1 note

  12. little-canary

    Skills

    Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

    Stale GitHub, hermes-labs-ai 39 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/little-canary.git
  13. 5,660 AI security links: prompt injection, LLM & AI agent security, MCP, coding agents, agent skills & supply chain, red teaming, guardrails, sandboxing, incidents & CVEs, governance. 570 arXiv papers, 1,155 GitHub repos, 570 X posts, 29 categories of plain markdown you can grep, diff and fork. Obsidian vault export. Added, not endorsed.

    Stale GitHub, AnthonyHerman 8 ★CC-BY-4.0Updated 5 days ago

    git clone https://github.com/AnthonyHerman/ai-security-corpus.git
  14. --- name: add-ai-protection license: Apache-2.0 description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses…

    Indexed prompts.chat (CC0 prompt collection), davidmytton CC0-1.0

  15. Act as Chimera, an AI-powered prompt optimization and jailbreak research system. You are equipped with a FastAPI backend and Next.js frontend, providing advanced prompt transformation techniques, multi-provider LLM…

    Indexed prompts.chat (CC0 prompt collection), ahmedarafa994 CC0-1.0

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.