InnerVault

Library

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

Results

  1. AISafetyHot

    MCP servers

    AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.

    Indexed GitHub, wuyoscar 2,127 ★Custom licence (see repository)Updated today

    git clone https://github.com/wuyoscar/AISafetyHot.git
  2. ADR

    MCP servers

    ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

    Stale GitHub, uber 2,090 ★Apache-2.0Updated 16 days ago

    git clone https://github.com/uber/ADR.git
  3. Scans RAG content/scraped pages for indirect prompt injection

    Stale Official MCP Registry, io.github.4hmetuyar Updated 45 days ago 1 note

    @guardbee/mcp-prompt-injection-scanner@0.2.2
  4. Scans RAG content/scraped pages for indirect prompt injection

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

    @guardbee/mcp-prompt-injection-scanner@1.2.0
  5. Prompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.

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

  6. Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

    Stale Official MCP Registry, dev.agentdiet Updated 26 days ago 1 note

  7. Hybrid prompt-injection firewall (Llama Guard 3) & Brazil PII/secret masking via x402 Base USDC.

    Indexed Official MCP Registry, io.github.brunopompeo1 Updated today 1 note

  8. Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.

    Stale Official MCP Registry, dev.agentdiet Updated 26 days ago 1 note

  9. Check a shop, checkout or payment link, paid API or token before paying; prompt-injection scan.

    Stale Official MCP Registry, com.oroboros-design.angel Updated 2 days ago 2 notes

    angel-agent-guard@0.2.0
  10. agent-opfor

    MCP servers

    Open-source adversary emulation for AI agents and MCP servers.

    Stale GitHub, KeyValueSoftwareSystems 583 ★Custom licence (see repository)Updated 33 days ago

    git clone https://github.com/KeyValueSoftwareSystems/agent-opfor.git
  11. Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.

    Indexed Official MCP Registry, com.oroboros-design.angel Updated 2 days ago 1 note

  12. HMAC-signed zero-width invisible canary token generator and output response leak auditor

    Stale Official MCP Registry, io.github.alphaparkinc Updated 28 days ago 1 note

    https://github.com/Alpha-Park/genpark-prompt-injection-canary-leak-sentinel-skill/releases/download/v1.0.1/genpark-prompt-injection-canary-leak-sentinel-skill.mcpb
  13. Check text before your agent reads it: hidden instructions, invisible text and links that leak data.

    Stale Official MCP Registry, app.openkrill Updated 31 days ago 1 note

  14. 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

  15. Checks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls.

    Stale Official MCP Registry, com.oroboros-design.angel Updated 2 days ago 1 note

  16. The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 48 days ago 3 notes

    agent-prompt-injection-firewall-mcp@1.0.13
  17. nuguard

    MCP servers

    AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

    Indexed GitHub, NuGuardAI 71 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/NuGuardAI/nuguard.git
  18. invaris-agentsec

    MCP servers

    Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.

    Stale GitHub, invarislabs 23 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/invarislabs/invaris-agentsec.git
  19. 35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

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

  20. mcp-scanner

    MCP servers

    Security scanner for MCP servers, source trees, and packages, with explicit findings and coverage reporting.

    Indexed GitHub, devlab-group 35 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/devlab-group/mcp-scanner.git
  21. 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
  22. guardana

    MCP servers

    Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

    Indexed GitHub, guardana 225 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/guardana/guardana.git
  23. pic-standard

    MCP servers

    Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.

    Stale GitHub, pic-standard 70 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/pic-standard/pic-standard.git
  24. mcp-audit-tool

    MCP servers

    🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

    Stale GitHub, graygnatconsole 543 ★MITUpdated 23 days ago

    git clone https://github.com/graygnatconsole/mcp-audit-tool.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.