InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

1,096 results with any of your words Clear search and filters
  1. Onça Setorial

    MCP servers

    Brazilian regulator data: CVM filings, dam safety, airline punctuality, rules, enforcement

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

  2. Complitas

    MCP servers

    For Complitas customers: use your Complitas building safety compliance account (account required)

    Indexed Official MCP Registry, uk.co.complitas Updated 2 days ago 1 note

  3. ProofPass

    MCP servers

    Current safety data sheets and product documents from manufacturers; EU deadlines and duties.

    Indexed Official MCP Registry, eu.proofpass Updated 2 days ago 1 note

  4. oasis

    Skills

    The open-source coding agent for any model: terminal and self-hosted web app, Claude Code plugins, subagents, and work that is actually verified.

    Indexed GitHub, FAHTHIZ 5 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/FAHTHIZ/oasis.git
  5. Pro Tailscale workflows for every device you own, run by your AI agent with a safety tier on every command. Community skill, not affiliated with Tailscale.

    Stale GitHub, cathrynlavery 11 ★MITUpdated 26 days ago

    git clone https://github.com/cathrynlavery/tailscale-superpowers.git
  6. futureagievals-mcp

    MCP servers

    A paid remote MCP for AI SDK eval dashboard, built to return verdicts, receipts, usage logs, and aud

    Stale Official MCP Registry, com.clauxel.futureagievals Updated 5 months ago 1 note

  7. Vellarin Hub

    MCP servers

    Apps with human approval, shared memory, a run log and evals for your agent. One URL, one key.

    Stale Official MCP Registry, ai.vellarin.hub Updated 4 days ago 1 note

  8. little-canary

    Skills

    Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

    Stale GitHub, hermes-labs-ai 39 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/hermes-labs-ai/little-canary.git
  9. boundaryai

    MCP servers

    Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.

    Stale Official MCP Registry, ai.boundaryai Updated 3 months ago 1 note

  10. Enoki

    MCP servers

    Test your AI agents for security and safety weaknesses, and re-verify the fixes.

    Stale Official MCP Registry, ai.enokilabs Updated 36 days ago 1 note

  11. GuildControl MCP

    MCP servers

    Safety-first MCP server for Discord with privacy-safe reads, audits, and reviewed administration

    Stale Official MCP Registry, app.lasers.guildcontrol Updated 4 days ago 2 notes

    guildctl@2.3.9
  12. NodeRooms Discovery

    MCP servers

    Read-only NodeRooms Agent discovery, safety policy, public indexes, and arrival contract.

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

  13. agentiam-mcp

    MCP servers

    Stdio MCP wrapper for AgentIAM's 18 x402 endpoints — agent safety + intelligence on Base.

    Stale Official MCP Registry, io.github.achilliesbot Updated 6 months ago

  14. EP AgentIAM

    MCP servers

    AI agent execution safety via x402 micropayments: risk scoring, integrity, memory checks

    Stale Official MCP Registry, io.github.achilliesbot Updated 7 months ago 1 note

  15. 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
  16. queryshield

    MCP servers

    Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.

    Stale Official MCP Registry, io.github.bch1212 Updated 6 months ago 2 notes

    queryshield-mcp@1.0.1
  17. mongo-scout-mcp

    MCP servers

    Scout your MongoDB databases with AI - safety features, live monitoring, and data quality

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

    mongo-scout-mcp@1.0.3
  18. calllint

    MCP servers

    Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.

    Stale Official MCP Registry, io.github.calllint Updated 25 days ago 1 note

    calllint-mcp@0.2.1
  19. Channel-safety for cold outreach: volume limits, SPF/DKIM/DMARC, spam-trigger auditing.

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

    outreach-deliverability-mcp@1.0.2
  20. K-Work Trust

    MCP servers

    Korean business record validation and workflow safety gates for AI agents.

    Stale Official MCP Registry, io.github.hycore220 Updated 6 months ago 1 note

  21. agent-guard

    MCP servers

    Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

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

    agent-tripwire@0.2.1
  22. sw-postgres-mcp

    MCP servers

    Safe-write Postgres MCP server with preview-before-execute writes and rollback safety.

    Stale Official MCP Registry, io.github.jpka Updated 3 months ago 2 notes

    sw-postgres-mcp@0.3.1
  23. agent-guard-mcp

    MCP servers

    Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.

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

    @liminallablibs/agent-guard-mcp@0.2.1
  24. Model-agnostic computer-use MCP: screenshot, safety-gated actions, Windows UIA targeting.

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

    open-compute-mcp@0.1.0-alpha.6

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.