InnerVault

Library

85,762 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. agent-cost-mcp-server

    MCP servers

    Prices LLM/agent runs per successful task, with spend recording and budget status.

    Stale Official MCP Registry, io.github.karmendra8386 Updated 14 days ago 1 note

    agent-cost-mcp-server@0.1.1
  2. nervous-system

    MCP servers

    Governance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.

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

    mcp-nervous-system@1.12.1
  3. rlg-mcp

    MCP servers

    MCP server exposing rlg log streams to LLM agents via JSON-RPC 2.0 over stdio.

    Stale Official MCP Registry, io.github.sebastienrousseau Updated 10 days ago 1 note

    ghcr.io/sebastienrousseau/rlg-mcp:0.0.18
  4. garnet-mcp

    MCP servers

    RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.

    Stale Official MCP Registry, io.github.tarazou9 Updated 3 months ago 1 note

    GarnetMcp.Server@0.1.2
  5. 4words

    MCP servers

    Ephemeral text/file sharing and real-time multi-agent chat rooms for LLM agents and humans.

    Stale Official MCP Registry, land.aletheia Updated 26 days ago 1 note

  6. KiCad Workbench

    MCP servers

    Gives KiCad 8, 9 and 10 projects to LLM agents: schematics, boards, ERC, DRC, BOM, edits

    Stale Official MCP Registry, io.github.turbyho Updated 9 days ago 1 note

    kicad-workbench@0.1.0
  7. ⚡ Drop-in SKILL.md, .cursorrules, CLAUDE.md, AGENTS.md & Remote MCP (.mcp.json) pack for Claude Code, Cursor, Windsurf, Cline & x402 AI Agents — Verify GitHub Bounties & Mine DOOM/wDOOM on Base Mainnet.

    Stale GitHub, doomsday-network 7 ★Updated 23 days ago

    git clone https://github.com/doomsday-network/web3-agent-skills.git
  8. Event-sourced world model for multi-LLM agents: propose, validate, and read a shared state.

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

  9. git-courer

    MCP servers

    Full git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing.

    Stale Official MCP Registry, io.github.Alejandro-M-P Updated 5 months ago

  10. temporal-mcp

    MCP servers

    Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.

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

    temporal-mcp@0.2.0
  11. vision-squeezer

    MCP servers

    Shrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.

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

    vision-squeezer@0.9.0
  12. data-profiler-mcp

    MCP servers

    Profiles CSV/Parquet/Excel/JSON files: schema, stats, quality flags and dtype tips for LLM agents.

    Stale Official MCP Registry, io.github.haiiibin Updated 39 days ago 1 note

    data-profiler-mcp@0.4.0
  13. plateau-creative-mcp

    MCP servers

    PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.

    Stale Official MCP Registry, io.github.pixelx-jp Updated 5 months ago 1 note

    @yodolabs/plateau-creative-mcp@0.1.1
  14. Jailbreak resistance tester for LLM agents: DAN, role-play, encoding bypass probes.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 14 days ago 1 note

  15. LLM Security Scanner

    MCP servers

    LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 14 days ago 1 note

  16. vital

    Skills

    AI-first personal OS: capture → execute → reflect. Todos, read-later, habits & reports in one calm, self-hosted workspace, with a resident agent + Claude/Codex skill. AI First 的个人操作系统:收集(Inbox)→ 执行(Todos)→ 复盘(Reports),单用户自托管。

    Stale GitHub, ximing 5 ★Updated 19 days ago

    git clone https://github.com/ximing/vital.git
  17. Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

    Stale Official MCP Registry, io.github.4hmetuyar Updated 50 days ago 1 note

    @guardbee/mcp-unbounded-consumption-auditor@0.1.2
  18. Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

    Stale Official MCP Registry, io.github.GuardBee Updated 18 days ago 1 note

    @guardbee/mcp-unbounded-consumption-auditor@0.3.1
  19. context-doctor

    MCP servers

    Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures.

    Indexed Official MCP Registry, io.github.KushalP1 Updated yesterday 1 note

    context-doctor@0.49.0
  20. page2md

    MCP servers

    Turn any webpage into clean Markdown for LLM/agent pipelines. Free tier; paid 1 USDC = 1000 req.

    Stale Official MCP Registry, net.bigfloppy.page2md Updated 23 days ago 1 note

  21. model-citizen

    Skills

    The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

    Stale GitHub, JakeSelby 24 ★MITUpdated 33 days ago

    git clone https://github.com/JakeSelby/model-citizen.git
  22. skill-olympus

    Skills

    Twelve Greek gods. One command. A working SaaS. 98 skills + 49 agents + 13 hooks for Claude Code + Codex CLI + Gemini CLI. Cross-CLI persistent memory, zero-interaction full pipeline (design → build → inspect → test → ship).

    Indexed GitHub, Dannykkh 7 ★MITUpdated 2 days ago

    git clone https://github.com/Dannykkh/skill-olympus.git
  23. Discuss ideas and uncertainty with LLM agents: join, browse threads, start discussions and reply.

    Stale Official MCP Registry, ch.greenwave.wall-x Updated 30 days ago 1 note

  24. Prompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 14 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.