InnerVault

Library

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

Results

  1. Husk

    MCP servers

    Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs

    Stale Official MCP Registry, io.github.husk-security Updated 2 months ago 1 note

    husk-sec@0.1.2
  2. ctxfw

    MCP servers

    Zero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.

    Indexed Official MCP Registry, io.github.heuristicolab Updated today 1 note

    ctxfw@4.2.0
  3. stock-sentinel

    MCP servers

    US stock attack/defense macro signals: 4-dimension framework, 26-year backtested. Research only.

    Stale Official MCP Registry, io.github.SheldonZhuang Updated 23 days ago 2 notes

    stock-sentinel-mcp@1.1.0
  4. mcp-kinetic-gain

    MCP servers

    75-tool MCP server for 12 Kinetic Gain specs and DefenseTech checks.

    Stale Official MCP Registry, io.github.mizcausevic-dev Updated 39 days ago 2 notes

    mcp-kinetic-gain@0.10.0
  5. A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant briefings). Enforces action titles, structured argument, exhibit discipline, citation standards, and communication-first design. Works alongside Anthropic's built-in PPTX skill.

    Stale GitHub, Gabberflast 1,184 ★MITUpdated 4 months ago

    git clone https://github.com/Gabberflast/academic-pptx-skill.git
  6. MCP stdio ShellGuard

    MCP servers

    Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.

    Stale Official MCP Registry, io.studiomeyer Updated 15 days ago 1 note

    mcp-stdio-shellguard@0.1.3
  7. BlueTeamJobs

    MCP servers

    Search open defensive cybersecurity (blue team) jobs and salary data. Read-only, no sign-in.

    Stale Official MCP Registry, com.blueteamjobs Updated 15 days ago 1 note

  8. Moscow extreme and defensive driving school: courses, programs, gift certificates, ordering.

    Indexed Official MCP Registry, ru.extrimdrive Updated today 1 note

  9. Shodan Search MCP

    MCP servers

    Defensive Shodan search and host intelligence MCP using customer-provided SHODAN_API_KEY for

    Stale Official MCP Registry, net.nexlab Updated 2 months ago 1 note

  10. Defensive vulnerability intelligence search across public CVE/NVD and GitHub advisory APIs with CVSS

    Stale Official MCP Registry, net.nexlab Updated 2 months ago 1 note

  11. Mitigant

    MCP servers

    Run real, auto-recovered cloud attacks on AWS, Azure and GCP to test your defenses.

    Stale Official MCP Registry, io.github.mitigant Updated 22 days ago 1 note

  12. Security MCP

    MCP servers

    Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses

    Stale Official MCP Registry, io.github.pratham-jain33 Updated 47 days ago 1 note

    security-mcp@0.1.1
  13. Aegis Security Skills

    MCP servers

    Read-only library of 24 defensive cybersecurity skills: ATT&CK, ATLAS, DFIR, CTEM and more.

    Stale Official MCP Registry, io.github.drupadsachania Updated 34 days ago 2 notes

    aegis-skills@1.5.0
  14. A curated corpus of incidents, attack vectors, failure modes, and defensive tools for autonomous AI agents.

    Stale GitHub, h5i-dev 57 ★MITUpdated 32 days ago

    git clone https://github.com/h5i-dev/awesome-ai-agent-incidents.git
  15. DoD Contract Announcements MCP — the daily press-release feed of every US defense contract award…

    Stale Official MCP Registry, io.github.pipeworx-io Updated 15 days ago 3 notes

    @pipeworx/mcp-dod-contract-announcements@0.2.1
  16. Evaluate startup distribution moat defensibility (Tier 1-5) and pre-seed valuation dispersion.

    Stale Official MCP Registry, com.modevc Updated 29 days ago 1 note

  17. Real-time capital oversight, drawdown alerts, and news blackout defense for funded prop traders.

    Stale Official MCP Registry, io.github.Ansarii Updated 2 months ago 1 note

  18. Query 38 empirical AI market charts, evaluate distribution defensibility, and search 3,650+ VCs.

    Stale Official MCP Registry, com.modevc Updated 29 days ago 1 note

  19. 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
  20. Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.

    Indexed GitHub, OWASP 204 ★Apache-2.0Updated yesterday

    git clone https://github.com/OWASP/www-project-agent-memory-guard.git
  21. JSON healing, O(n) ReDoS defense, XML prompt compilation, and schema verification tools.

    Stale Official MCP Registry, io.github.stand-out-of-my-sun Updated 27 days ago 1 note

  22. Smart contract audit oracles, Solana risk analysis, MEV defense & HTTP 402 verifiers.

    Stale Official MCP Registry, io.github.stand-out-of-my-sun Updated 27 days ago 1 note

  23. mastyf.ai

    MCP servers

    Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.

    Stale GitHub, mastyf-ai 21 ★AGPL-3.0Updated 9 days ago

    git clone https://github.com/mastyf-ai/mastyf.ai.git
  24. 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

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.