InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Mcpwn

    MCP servers

    Automated security scanner for Model Context Protocol servers that detects RCE, path traversal, prompt injection, and protocol vulnerabilities.

    Stale GitHub, Teycir 31 ★MITUpdated 32 days ago

    git clone https://github.com/Teycir/Mcpwn.git
  2. ave

    MCP servers

    AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.

    Stale GitHub, aveproject 24 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/aveproject/ave.git
  3. 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 10 days ago

    git clone https://github.com/mastyf-ai/mastyf.ai.git
  4. An open database of real-world AI agent incidents.

    Stale GitHub, Continuum-AI-Corp 30 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/Continuum-AI-Corp/Orca-AI-Incident-Archive.git
  5. cfgaudit

    MCP servers

    Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, OWASP LLM Top 10 mapping.

    Indexed GitHub, cfgaudit 27 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/cfgaudit/cfgaudit.git
  6. jev-judge-mcp

    MCP servers

    Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

    Stale GitHub, PyModel 48 ★MITUpdated 33 days ago

    git clone https://github.com/PyModel/jev-judge-mcp.git
  7. mcp-safeguard

    MCP servers

    MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

    Stale Official MCP Registry, com.cognivators Updated 5 months ago 1 note

    mcp-safeguard@0.3.2
  8. AI Firewall MCP

    MCP servers

    Multi-agent LLM security layer detecting prompt injection and jailbreaks.

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

    ai-firewall-mcp@1.0.1
  9. injectshield

    MCP servers

    Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

    Stale Official MCP Registry, io.github.bch1212 Updated 6 months ago 2 notes

    @injectshield/mcp@0.1.4
  10. promptrejectormcp

    MCP servers

    Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.

    Stale Official MCP Registry, io.github.revsmoke Updated 9 months ago 2 notes

    prompt-rejector@1.0.1
  11. GuardianShield

    MCP servers

    AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs

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

    guardianshield@1.2.1
  12. paysafe

    MCP servers

    Payment firewall for x402: scans for replay, overpayment, PII/secret leaks, prompt-injection.

    Stale Official MCP Registry, com.paysafe-agent Updated 4 months ago 1 note

    paysafe-x402@1.1.1
  13. ToolTrust Scanner

    MCP servers

    Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.

    Stale Official MCP Registry, io.github.AgentSafe-AI Updated 7 months ago 1 note

    tooltrust-mcp@1.0.9
  14. agentshield-mcp

    MCP servers

    Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

    Stale Official MCP Registry, io.github.dl-eigenart Updated 7 months ago 2 notes

    @eigenart/agentshield-mcp@0.1.3
  15. Zyrax Guard

    MCP servers

    Audit AI agent configs for prompt injection & rogue MCP servers; vet packages

    Stale Official MCP Registry, io.github.tiagosilva07 Updated 3 months ago 1 note

    zyrax-guard@0.13.0
  16. MCP-Bastion

    MCP servers

    Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.

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

    mcp-bastion-python@5.1.0
  17. cloakcheck

    MCP servers

    Scan a page for hidden prompt-injection payloads targeting AI agents.

    Stale Official MCP Registry, app.vercel.cloakcheck-wheat Updated 2 months ago 1 note

  18. kagami

    MCP servers

    Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.

    Stale Official MCP Registry, io.github.Hiroshi-Ichiyanagi Updated 42 days ago 2 notes

  19. Sentinel Scan

    MCP servers

    MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

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

    sentinel-scan-cli@1.4.16
  20. Tripwire

    MCP servers

    Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.

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

    tripwire-mcp@0.3.1
  21. Trentina

    MCP servers

    Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense

    Stale Official MCP Registry, io.github.crunchtools Updated 4 months ago 1 note

    mcp-trentina-crunchtools@0.5.0
  22. agent-immune

    MCP servers

    AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

    Stale Official MCP Registry, io.github.denial-web Updated 7 months ago 1 note

    agent-immune@0.2.2
  23. mcpm

    MCP servers

    MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

    Stale Official MCP Registry, io.github.getmcpm Updated 4 days ago 1 note

    @getmcpm/cli@0.54.0
  24. mcp-server

    MCP servers

    Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

    Stale Official MCP Registry, io.github.ingressward Updated 5 months ago 2 notes

    @ingressward/mcp-server@1.0.0

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.