InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Check seven declared HTTP security header families without returning raw values

    Stale Official MCP Registry, io.github.kriton-dev Updated 11 days ago 1 note

  2. Looks up a person's criminal record certificate at the Federal Police, from the CPF and name. Built

    Stale Official MCP Registry, io.github.mcp-dir Updated 3 months ago 1 note

  3. Check declared robots.txt permissions for six AI crawlers at URL paths

    Stale Official MCP Registry, io.github.kriton-dev Updated 14 days ago 1 note

  4. Gates an LLM agent's writes to an OPC UA server on ranges, rate of change and live interlocks.

    Stale Official MCP Registry, io.github.alikup-ai Updated 10 days ago 2 notes

    otgate@0.1.0
  5. Gates an LLM agent's writes to an OPC UA server on ranges, rate of change and live interlocks.

    Stale Official MCP Registry, io.github.alikup-ai Updated 10 days ago 1 note

    otgate@0.1.1
  6. Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

    Stale Official MCP Registry, io.github.agentwares Updated 2 months ago 1 note

  7. Check DNS records and email authentication (SPF, DKIM, DMARC) for domains, as findings by severity

    Stale Official MCP Registry, io.github.kriton-dev Updated 15 days ago 1 note

  8. authkestra

    MCP servers

    The Compile-Time Safe Identity & AI Agent Authorization Engine for Rust

    Indexed GitHub, Authkestra 31 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/Authkestra/authkestra.git
  9. Lex

    MCP servers

    Episodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.

    Stale Official MCP Registry, dev.smartergpt Updated 28 days ago 2 notes

    @smartergpt/lex-mcp@4.4.4
  10. norviq

    MCP servers

    Runtime security platform for LLM agent tool calls on Kubernetes

    Indexed GitHub, norviq-dev 27 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/norviq-dev/norviq.git
  11. cybersec-toolkit

    MCP servers

    MCP server that catalogs 670+ security tools and runs installed ones under a scope and audit policy.

    Indexed Official MCP Registry, io.github.26zl 87 ★Updated 3 days ago 1 note

    ghcr.io/26zl/cybersec-toolkit:1.5.0
  12. Lex

    MCP servers

    Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.

    Stale Official MCP Registry, io.github.Guffawaffle Updated 10 months ago 1 note

    @smartergpt/lex-mcp@1.0.2
  13. privacypage-mcp

    MCP servers

    Generate privacy policies, ToS, EULAs, cookie policies & disclaimers from your AI agent.

    Stale Official MCP Registry, io.github.rushi053 Updated 2 months ago 2 notes

    privacypage-mcp@0.1.0
  14. MCP Hangar

    MCP servers

    A policy enforcement plane for MCP: pins every tool, holds risky calls, enforces egress policy.

    Indexed Official MCP Registry, io.mcp-hangar Updated yesterday 1 note

    mcp-hangar@2.39.0
  15. Eclipse Capline

    MCP servers

    Sealed-policy cap bound proofs over fixture policies; recomputable certificate, local only.

    Stale Official MCP Registry, io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC Updated 21 days ago

  16. Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.

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

    agent-aegis@0.1.6
  17. Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes.

    Stale Official MCP Registry, com.actablesite Updated 4 months ago 1 note

  18. Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes.

    Stale Official MCP Registry, com.actablesite Updated 4 months ago 2 notes

  19. helm-ai-kernel

    MCP servers

    Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.

    Indexed GitHub, Mindburn-Labs 61 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/Mindburn-Labs/helm-ai-kernel.git
  20. Containarium

    MCP servers

    Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrough, MCP-native CLI

    Indexed GitHub, FootprintAI 318 ★Apache-2.0Updated yesterday

    git clone https://github.com/FootprintAI/Containarium.git
  21. 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 3 days ago

    git clone https://github.com/ThreeMoonsLab/agents-shipgate.git
  22. arkon

    MCP servers

    Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.

    Stale GitHub, nduckmink 1,493 ★Custom licence (see repository)Updated 5 months ago

    git clone https://github.com/nduckmink/arkon.git
  23. caura

    MCP servers

    Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

    Indexed GitHub, caura-ai 559 ★Apache-2.0Updated yesterday

    git clone https://github.com/caura-ai/caura.git
  24. kdcube

    MCP servers

    Open-source, self-hosted runtime and SDK for AI applications. One tenant/project deployment serves many users and apps with governed tools, scoped credentials, isolated generated code, and cost controls.

    Stale GitHub, kdcube 27 ★MITUpdated 10 days ago

    git clone https://github.com/kdcube/kdcube.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.