InnerVault

Library

87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Action-level governance for AI agents -- control what they DO, not what they SAY

    Stale Official MCP Registry, io.github.JarvisOnM4 Updated 8 months ago 1 note

    agent-guardrail@0.1.2
  2. agent-guard-mcp

    MCP servers

    Git-aware safe file ops for AI agents: delete anything except git-tracked source code.

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

    https://github.com/Kavachh/agent-guard-mcp/releases/download/v0.2.0/agent-guard-mcp_darwin_arm64@0.2.0
  3. Boundary Guard x402

    MCP servers

    MCP tools for x402 readiness, paid-path probes, launch packs, and trust receipts.

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

  4. agent-output-guard

    MCP servers

    Validate and verify data from other agents before acting on it. Zero LLM costs.

    Stale Official MCP Registry, io.github.agenson-horrowitz Updated 7 months ago 1 note

    @agenson-horrowitz/agent-output-guard-mcp@1.0.8
  5. guardrly-mcp

    MCP servers

    Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more

    Stale Official MCP Registry, io.github.fishcoco-code Updated 7 months ago 2 notes

    guardrly@0.1.3
  6. Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.

    Indexed Official MCP Registry, io.github.fredyee Updated yesterday 1 note

  7. supply-chain-guard

    MCP servers

    Supply-chain malware scanner and MCP server: vet packages in 15 ecosystems before install, offline.

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

    supply-chain-guard@6.6.1
  8. Infraveil Agent Guard

    MCP servers

    Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.

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

    infraveil-guard@0.1.1
  9. email-guard-mcp

    MCP servers

    Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.

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

    email-guard-mcp@1.3.0
  10. FabTally Guard

    MCP servers

    Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.

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

  11. PayPal, guarded

    MCP servers

    PayPal's Agent Toolkit with limits on refunds and the owner's Approve/Deny above them.

    Stale Official MCP Registry, io.github.Fizzl13 Updated 9 days ago 2 notes

    fizzl-paypal-guard-mcp@0.3.0
  12. Foo Guard Library

    MCP servers

    Search and read free, scanned AI agent skills and configs. Read-only, no account.

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

  13. n8n-guard

    MCP servers

    Read-only health checks for self-hosted n8n: datastore growth, stuck runs, retention, git drift.

    Stale Official MCP Registry, io.github.flow-84 Updated 6 days ago 2 notes

    n8n-guard@0.1.0
  14. bifrost

    MCP servers

    Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

    Indexed GitHub, maximhq 9,715 ★Apache-2.0Updated today

    git clone https://github.com/maximhq/bifrost.git
  15. Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.

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

  16. DB Query Guard MCP

    MCP servers

    Paid remote MCP for governed database query review, SQL simulation, approvals, and audits.

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

  17. Datumline Agent Guard

    MCP servers

    Checks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.

    Stale Official MCP Registry, io.github.datumline Updated 38 days ago 1 note

    datumline-agent-guard@0.2.0
  18. defi-guard-mcp

    MCP servers

    DeFi safety checks on Base before you sign: honeypot, owner-power scan, approval risk, Aave health.

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

    @iniit/defi-guard-mcp@0.2.0
  19. firestore-rules-guard

    MCP servers

    Audits firestore.rules and storage.rules for public access, expired test-mode dates and missing owne

    Stale Official MCP Registry, io.github.jmshinhwa Updated 56 days ago 1 note

    @readystack/firestore-rules-guard@1.0.4
  20. MCP Security Guard

    MCP servers

    Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).

    Indexed Official MCP Registry, io.github.petrovicistefan Updated yesterday 1 note

    mcp-security-guard@0.9.2
  21. Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

    Stale Official MCP Registry, io.github.rudimentall1 Updated 3 months ago 1 note

    agentic-wallet-guardian-mcp@3.1.0
  22. Local fit-check and safe integration guidance for non-custodial Base USDC agent transactions.

    Stale Official MCP Registry, kr.p-e.tollary Updated 2 months ago 1 note

    tollary@0.1.0
  23. Context Guardian

    MCP servers

    40 turns: 1,130,722 tokens upstream -> 161,141. A fail-open compaction proxy for local models.

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

    context-guardian@0.16.0
  24. TAS Guard

    MCP servers

    Order limits, phone approvals and a kill switch in front of any broker or exchange MCP server.

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

    tas-guard@0.5.1

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.