InnerVault

Library

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

Results

  1. nexus-mcp

    MCP servers

    Japanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.

    Stale Official MCP Registry, io.github.nexus-api-lab Updated 7 months ago 1 note

  2. sigma-gate

    MCP servers

    Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.

    Stale Official MCP Registry, io.github.spektre-labs Updated 4 months ago 1 note

  3. InjectScan

    MCP servers

    Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools

    Stale Official MCP Registry, io.github.agentgate-builder Updated 27 days ago 1 note

  4. AgentRead

    MCP servers

    Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning

    Stale Official MCP Registry, dev.workers.toolschemaforge.agent-read Updated 22 days ago 1 note

  5. GitHub Capability Router (666 repos, 96.4% token savings) & 5-Vector Prompt-Injection Firewall.

    Stale Official MCP Registry, io.github.Hadinkof Updated 8 days ago 1 note

  6. Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.

    Stale Official MCP Registry, io.github.asish-singh Updated 37 days ago 1 note

    agent-readiness-auditor@0.5.0
  7. Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats

    Stale Official MCP Registry, io.github.maco144 Updated 5 months ago 1 note

  8. Agent-Shield

    MCP servers

    Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.

    Stale Official MCP Registry, io.github.startekenterprises-ai Updated 8 days ago 1 note

  9. Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls

    Stale Official MCP Registry, io.github.vikasny30 Updated 2 months ago 2 notes

    aletheia-mcp@0.3.1
  10. 50-vector prompt-injection, llms.txt poisoning, SSRF & OpenAPI scanner ($1 USDC).

    Stale Official MCP Registry, com.run402.apishield-waf Updated 30 days ago 1 note

  11. Web pages for AI agents: may-I-use checks, prompt-injection flags, Markdown, JSON, screenshots

    Stale Official MCP Registry, com.bastionhelix Updated 19 days ago 1 note

  12. Power Strip Security

    MCP servers

    Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.

    Stale Official MCP Registry, io.github.AlbertBalestrini Updated 18 days ago 3 notes

    power-strip-security-mcp@0.2.0
  13. A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.

    Stale Official MCP Registry, ai.mails Updated 32 days ago 3 notes

    @mailsai/mcp-server@0.5.0
  14. site-audit

    MCP servers

    Discover a site's pages from its sitemap and sample them for WCAG and prompt-injection risk.

    Stale Official MCP Registry, com.edgethirteen.www Updated 2 months ago 1 note

  15. prompt-guard-mcp

    MCP servers

    Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex

    Stale Official MCP Registry, io.github.robertoyanguas-ops Updated 35 days ago 1 note

  16. Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.

    Stale Official MCP Registry, io.github.tylerscomic-lab Updated 47 days ago 1 note

  17. Agent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.

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

  18. Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

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

    tripwire-guard@0.4.2
  19. Web pages, JavaScript sites and PDFs to clean Markdown for AI agents, prompt injection removed.

    Stale Official MCP Registry, io.github.marcepalacios12 Updated 19 days ago 1 note

  20. Three fast safety checks for agents, each with a signed hash-chained receipt: (1) prompt-injection c

    Stale Official MCP Registry, com.scriptmasterlabs Updated 14 days ago 1 note

  21. Scan PDFs, Office docs, and RAG files for malware exploits, macros, CVEs, and AI prompt injection.

    Stale Official MCP Registry, com.malwaretracker Updated 5 days ago 3 notes

    malwaretracker-mcp@2.3.0
  22. Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring

    Stale Official MCP Registry, io.github.gaurav-kumar-sinha-060705 Updated 2 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.