InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. AI agent security audit: red-team probes plus missing-guardrail review with fixes.

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

  2. Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.

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

  3. AegisFlow

    MCP servers

    Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.

    Stale GitHub, saivedant169 39 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/saivedant169/AegisFlow.git
  4. AiEGIS

    MCP servers

    AI agent security and governance. Register, verify, scan, and monitor agents.

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

  5. WolfSMS

    MCP servers

    Let AI agents securely read the text messages on your phone.

    Stale Official MCP Registry, com.usewolfsms Updated 16 days ago 1 note

  6. agent-immune

    MCP servers

    AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

    Stale Official MCP Registry, io.github.denial-web Updated 7 months ago 1 note

    agent-immune@0.2.2
  7. shellward

    MCP servers

    AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.

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

    shellward@0.5.11
  8. agents-shipgate

    MCP servers

    The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

    Indexed GitHub, ThreeMoonsLab 87 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/ThreeMoonsLab/agents-shipgate.git
  9. PO6 Mailbox

    MCP servers

    Give AI agents secure access to your email via private aliases with dedicated mailbox storage.

    Stale Official MCP Registry, com.po6 Updated 9 months ago 1 note

  10. gsep-mcp

    MCP servers

    AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.

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

    @gsep/mcp@1.0.2
  11. zerno-lite

    MCP servers

    Give AI agents secure access to ZERNO project briefs, tasks, and context over remote MCP.

    Stale Official MCP Registry, one.zerno Updated 5 months ago 1 note

  12. Agent Coach (Upskill)

    MCP servers

    Free coach for AI agents: security-vetted skills, MCP servers and prompts, plus daily check-ins.

    Stale Official MCP Registry, coach.upskill Updated 6 days ago 1 note

  13. AI agent security, MCP 2026 schema & graph audits, <250ms guardrails, and compliance dossiers

    Indexed Official MCP Registry, io.github.bobcar0 Updated 2 days ago 3 notes

    @systemores/systemores-plugin@1.2.0
  14. RevDesk Product MCP

    MCP servers

    Give AI agents secure access to RevDesk calling, SMS, phone numbers, caller IDs, and usage.

    Stale Official MCP Registry, io.github.cell-labs-inc Updated 2 months ago 1 note

  15. grantex

    MCP servers

    grantex is the identity, authorization, and audit infrastructure for AI agents — the "OAuth moment" for the agentic internet. We provide a universal SDK and cloud service that lets any AI agent act on behalf of a human with scoped, revocable permissions, cryptographic identity, and an immutable audit trail. Developers integrate in minutes.

    Indexed GitHub, mishrasanjeev 34 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/mishrasanjeev/grantex.git
  16. Read AI security guides and lab research, and request an LLM or AI agent security assessment.

    Stale Official MCP Registry, com.airedteamingservices Updated 6 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.