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. Identity-first enterprise MCP gateway: per-call authorization, agent identity and audit trail

    Stale Official MCP Registry, com.secureauth Updated 24 days ago 1 note

  2. x402 agent preflight: exact action authority plus payment mandate, destination, expiry and replay.

    Stale Official MCP Registry, io.github.speeedy10 Updated 46 days ago 2 notes

  3. agent-passport-system

    MCP servers

    Open protocol and TypeScript SDK for AI agent authority: identity, scoped delegation, enforcement before the action, and signed receipts.

    Indexed GitHub, agent-passport-system 67 ★Apache-2.0Updated today

    git clone https://github.com/agent-passport-system/agent-passport-system.git
  4. tenuo

    Agents & frameworks

    Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.

    Stale GitHub, tenuo-ai 106 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/tenuo-ai/tenuo.git
  5. Risk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.

    Stale GitHub, dancingteeth 19 ★MITUpdated 4 days ago

    git clone https://github.com/dancingteeth/unified-code-review.git
  6. CrawlConsole

    MCP servers

    Backlink Analysis MCP for AI Agents: authority, referring domains, and competitor link gaps.

    Stale Official MCP Registry, com.crawlconsole Updated 6 months ago 2 notes

    @crawlconsole/mcp@0.1.4
  7. particlr-mcp

    MCP servers

    Agents author particlr .prt particle effects headlessly: validate, simulate, render to PNG, patch.

    Stale Official MCP Registry, io.github.brac Updated 3 days ago 1 note

    @particlr/mcp@0.3.1
  8. PolicyLayer

    MCP servers

    The system of record for AI agent authority: playbooks, routed policy questions, reusable rules.

    Stale Official MCP Registry, com.policylayer Updated 3 months ago 1 note

  9. qauth

    MCP servers

    Open-source identity for the agent era: an OAuth 2.1 and OpenID Connect server for apps, MCP servers and AI agents, with federation and post-quantum signing. Self-hostable.

    Indexed GitHub, qauth-labs 28 ★Apache-2.0Updated today

    git clone https://github.com/qauth-labs/qauth.git
  10. Issue Agent Passports and verify agent authority before value moves. Signed verification records.

    Stale Official MCP Registry, network.flint Updated 4 months ago 1 note

  11. LiveGraph

    MCP servers

    Live, editable canvas for AI agents — author graphs via MCP, then watch and reroute runs live.

    Stale Official MCP Registry, ai.livegraph Updated 14 days ago 1 note

  12. authkestra

    MCP servers

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

    Indexed GitHub, Authkestra 31 ★Apache-2.0Updated yesterday

    git clone https://github.com/Authkestra/authkestra.git
  13. VOC OpenAPI MCP

    MCP servers

    VOC OpenAPI gives AI agents authorized review and product data for insights, tagging, and listings.

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

  14. magpie

    Skills

    Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.

    Indexed GitHub, apache 145 ★Apache-2.0Updated today

    git clone https://github.com/apache/magpie.git
  15. Agent-Skills

    Skills

    Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

    Stale GitHub, jscraik 9 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/jscraik/Agent-Skills.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.