InnerVault

Library

85,762 resources from 11 public sources. 54 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. cordum

    MCP servers

    The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

    Indexed GitHub, cordum-io 510 ★Custom licence (see repository)Updated today

    git clone https://github.com/cordum-io/cordum.git
  3. sqz

    MCP servers

    Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.

    Stale Official MCP Registry, io.github.ojuschugh1 648 ★Updated 4 days ago 1 note

    sqz-mcp@2.2.0
  4. webmcp-react

    MCP servers

    React hooks for exposing your app's functionality as WebMCP tools - transport-agnostic, SSR-safe, Strict Mode safe, W3C spec-aligned

    Stale GitHub, agentcathq 91 ★MITUpdated 25 days ago

    git clone https://github.com/agentcathq/webmcp-react.git
  5. huqan

    MCP servers

    Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.

    Stale GitHub, ali-ulu 30 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/ali-ulu/huqan.git
  6. skybridge

    MCP servers

    Skybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platform-agnostic.

    Stale GitHub, alpic-ai 2,162 ★MITUpdated 33 days ago

    git clone https://github.com/alpic-ai/skybridge.git
  7. sysknife

    MCP servers

    An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.

    Indexed GitHub, lacs-project 280 ★MITUpdated yesterday

    git clone https://github.com/lacs-project/sysknife.git
  8. Sonicmatch

    MCP servers

    Analyze video mood and pace, then recommend license-safe BGM with a mix spec.

    Stale Official MCP Registry, io.github.js713-lab 153 ★MITUpdated 26 days ago 2 notes

    https://github.com/js713-lab/sonic-match-mcp/releases/download/v0.2.0/sonicmatch-mcp-0.2.0.mcpb
  9. StatCraft

    MCP servers

    High-performance, memory-safe, and open-source statistical analysis package in 100% pure Safe Rust

    Indexed GitHub, kobaltgit 52 ★Apache-2.0Updated yesterday

    git clone https://github.com/kobaltgit/StatCraft.git
  10. Pakistan payments for AI agents — Safepay checkout via Safepay. Never holds funds.

    Stale Official MCP Registry, app.wishpool Updated 4 months ago 1 note

  11. joltrin

    MCP servers

    Durable memory and a verification barrier for AI agents, in one embedded Go library.

    Stale GitHub, SharedCode 27 ★MITUpdated 9 days ago

    git clone https://github.com/SharedCode/joltrin.git
  12. Manage functional-safety requirements and lifecycle traceability.

    Stale Official MCP Registry, io.github.vwnb Updated 9 days ago 1 note

  13. plip-oss

    MCP servers

    Open-source runtime for grounded, model-agnostic computer-use agents with verifiable action receipts.

    Stale GitHub, hussainn7 39 ★MITUpdated 9 days ago

    git clone https://github.com/hussainn7/plip-oss.git
  14. 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
  15. 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
  16. rocketmq-rust

    MCP servers

    🚀 Apache RocketMQ built in Rust 🦀 — faster, safer, and more memory-efficient. Powering high-performance messaging for the AI era, with AI Agent, MCP, and AI-SRE capabilities.

    Indexed GitHub, mxsm 1,545 ★Apache-2.0Updated today

    git clone https://github.com/mxsm/rocketmq-rust.git
  17. Read SafetyChain food safety records, CAPAs, forms, suppliers, items, locations and equipment.

    Indexed Official MCP Registry, io.usefulapi Updated today 1 note

  18. Safe header name check

    Stale Official MCP Registry, io.github.sadri-dridi Updated 2 months ago 1 note

  19. AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.

    Stale Official MCP Registry, io.github.OjasKord Updated 4 months ago 3 notes

    url-safety-validator-mcp@1.2.27
  20. SafetyDataSheetAPI

    MCP servers

    Extract safety data sheet (SDS/MSDS) PDFs into a fixed 16-section JSON record.

    Stale Official MCP Registry, com.safetydatasheetapi Updated 22 days ago 1 note

  21. SafeLagoon

    MCP servers

    Connect a SafeLagoon parent account to check screen time and manage family device rules.

    Stale Official MCP Registry, com.safelagoon Updated 4 days ago 1 note

  22. Deterministic pre-execution safety certification for autonomous AI agents.

    Stale Official MCP Registry, io.github.tb8412 Updated 8 months ago 1 note

    qae-safety@0.1.2
  23. safetyreplay-mcp

    MCP servers

    Paid remote MCP for safety replays, policy gates, eval receipts, and release evidence.

    Stale Official MCP Registry, com.clauxel.safetyreplay Updated 6 months ago 1 note

  24. NHTSA Vehicle Safety

    MCP servers

    Vehicle safety recalls, complaints, and crash data from NHTSA

    Stale Official MCP Registry, com.olyport Updated 7 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.