InnerVault

Library

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

Results

  1. Boardcheck

    MCP servers

    Flags deceptive signals in AI-agent marketplace listings, from fake engagement to prompt injection

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

    https://github.com/Echolonius/boardcheck/releases/download/v0.8.1/boardcheck-mcp-0.8.1.mcpb@0.8.1
  2. YUSA

    MCP servers

    Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.

    Stale Official MCP Registry, io.github.yusasecurity Updated 3 days ago 1 note

    https://github.com/yusasecurity/yusa/releases/download/v0.3.5/yusa.mcpb
  3. GEO Shield

    MCP servers

    Detects hidden AI prompt injection, AI recommendation poisoning, sneaky redirects and hidden spam.

    Stale Official MCP Registry, io.github.krishnaGauss Updated 5 days ago 1 note

    geo-shield-mcp@0.1.0
  4. pgwarden

    MCP servers

    Governed Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced read-only queries, PII masking, human-approved writes, a tamper-evident audit log, a red-team suite and Terraform for Cloud Run.

    Stale GitHub, B0yko 23 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/B0yko/pgwarden.git
  5. AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.

    Stale Official MCP Registry, com.skillssafe Updated 8 months ago 2 notes

    skillssafe-mcp@1.0.0
  6. ai-code-scanner

    MCP servers

    Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

    Stale Official MCP Registry, io.github.4hmetuyar Updated 50 days ago 1 note

    @guardbee/mcp-ai-code-scanner@0.3.2
  7. ai-code-scanner

    MCP servers

    Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

    Stale Official MCP Registry, io.github.GuardBee Updated 18 days ago 1 note

    @guardbee/mcp-ai-code-scanner@0.5.1
  8. TrustFetch

    MCP servers

    Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.

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

  9. zentric-protocol-mcp

    MCP servers

    Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.

    Stale Official MCP Registry, io.github.ZentricProtocol Updated 6 months ago 1 note

    zentric-protocol-mcp@0.1.3
  10. pylos-mcp

    MCP servers

    Email MCP server for Gmail, Outlook and any IMAP mailbox, hardened against prompt injection

    Stale Official MCP Registry, io.github.adamVass Updated 14 days ago 2 notes

    pylos-mcp@1.4.0
  11. lu

    MCP servers

    lu.ma events MCP server with draft+confirm safety, audit logging, and prompt-injection scrubbing.…

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

    https://github.com/adelaidasofia/luma-mcp/releases/download/v0.1.0/luma-mcp.mcpb@0.1.0
  12. Breach, SIM swap, infostealer, domain lookalikes, MCP registry risk, prompt-injection detection.

    Stale Official MCP Registry, io.github.nzdsf2-gif Updated 52 days ago 2 notes

    relayshield-mcp@0.3.0
  13. mcp-armor

    MCP servers

    Security sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks.

    Stale Official MCP Registry, io.studiomeyer Updated 16 days ago 1 note

    ghcr.io/studiomeyer-io/mcp-armor:0.8.2
  14. SecurityScan

    MCP servers

    Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.

    Stale Official MCP Registry, net.apisecurityscan Updated 8 months ago 1 note

  15. tech-risk

    MCP servers

    MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable

    Stale Official MCP Registry, ai.greyridgesignals Updated 13 days ago 2 notes

    greyridge-x402-tools@0.8.2
  16. Prescan

    MCP servers

    Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check.

    Stale Official MCP Registry, xyz.canisell Updated 15 days ago 1 note

  17. InjectScan

    Public APIs

    Scores text, web pages and MCP tool definitions for prompt injection with deterministic rules

    Indexed public-apis (GitHub list) 1 note

  18. SLF Guardian

    MCP servers

    Safety checks an agent runs before it acts: packages, commands, prompt injection, links, code.

    Indexed Official MCP Registry, io.github.slfguardian Updated 2 days ago 2 notes

    slf-guardian-mcp@1.2.0
  19. mcp-audit

    MCP servers

    Security audit for MCP servers: command injection, unsafe file access, secrets, prompt injection.

    Indexed Official MCP Registry, top.web3project Updated yesterday 1 note

  20. 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 19 days ago 3 notes

    @safeprompt.dev/mcp@0.1.1
  21. 1Claw Vault

    MCP servers

    HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.

    Stale Official MCP Registry, io.github.1clawAI Updated 2 months ago 2 notes

    @1claw/mcp@0.56.3
  22. Scan for prompt injection, secrets, PII, and vet MCP servers before installation

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

    @weave_protocol/mund@0.1.12
  23. agentforge

    MCP servers

    Safety checks for AI agents: preflight before signing, prompt-injection scan, sanctions, rug checks.

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

  24. CanaryGuard 402

    MCP servers

    Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base.

    Stale Official MCP Registry, io.github.ak10082247-max Updated 33 days 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.