InnerVault

Library

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

Results

  1. Dejo

    MCP servers

    A browser your AI agent remembers. Learn a site once, replay it in one call, zero model calls.

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

    dejo-mcp@0.5.1
  2. Kizuki RAG Ingest

    MCP servers

    YouTube transcripts (chunks, phrase search, most replayed moments), PDFs and web pages as Markdown.

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

  3. Overwatch 2 MCP for hero meta, public player stats, replays, patch notes, and OWCS Korea.

    Stale Official MCP Registry, io.github.BK927 Updated 2 months ago 1 note

    https://github.com/BK927/overwatch-aio/releases/download/v0.3.2/overwatch-aio-0.3.2.mcpb
  4. Webhook Toolkit

    MCP servers

    Webhook URLs for AI agents: receive, wait for, replay, sign and verify webhooks (Stripe, GitHub…).

    Stale Official MCP Registry, io.github.THE-KIPDEV Updated 59 days ago 3 notes

    webhook-toolkit@0.1.1
  5. Pre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.

    Stale Official MCP Registry, io.github.presidio-v Updated 9 days ago 1 note

    presidio-hardened-x402-mcp@0.4.0
  6. 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

  7. agent-theatre

    MCP servers

    Watch your coding agent work as a film: opens and replays the Agent Theatre stage for a repo.

    Stale Official MCP Registry, io.github.shreyassaw5394 Updated 12 days ago 1 note

    agent-theatre@1.9.0
  8. postgame.lol

    MCP servers

    League of Legends coaching from your own replays: the mistakes that cost you and what to fix.

    Stale Official MCP Registry, lol.postgame Updated 15 days ago 1 note

  9. Instagram Direct, profiles, search, posts, comments, and likes via mobile API replay.

    Stale Official MCP Registry, co.civai.nova Updated 14 days ago 1 note

  10. scrapewright

    MCP servers

    Give it a URL, get structured rows. A model writes the parser once; replays are free.

    Stale Official MCP Registry, io.github.Ozymandias-Owens-2 Updated 48 days ago 3 notes

    scrapewright@1.0.3
  11. mcp-server

    MCP servers

    The stock market, in SQL — scan, replay, or subscribe across ~12k US tickers and top 100 cryptos.

    Stale Official MCP Registry, io.github.tickerbot Updated 5 months ago 3 notes

    @tickerbot/mcp-server@0.1.3
  12. Agentboard Skills

    MCP servers

    Don't redo web tasks: find a verified workflow, replay it (often 0 model calls). Failures shown.

    Stale Official MCP Registry, io.github.jai-rathore Updated 17 days ago 1 note

  13. OpenClaw GenPark Envoy - Inter-agent mutual handshake and secure HMAC authenticated envelope router with replay attack prevention.

    Stale GitHub, alphaparkinc 7 ★MITUpdated 16 days ago

    git clone https://github.com/alphaparkinc/openclaw-genpark-envoy.git
  14. Menso

    MCP servers

    AI users run real tasks on your live site and show where they get stuck, with a replay of every step

    Stale Official MCP Registry, io.menso Updated 48 days ago 1 note

  15. sprawling-agents

    Agents & frameworks

    🏙️ A city of AI agents on your machine where nothing is hidden: prompts are plain files you own, and every context is a line in a hash-chained, offline-verifiable Ledger you can replay.

    Indexed GitHub, 2youg1 109 ★MPL-2.0Updated today

    git clone https://github.com/2youg1/sprawling-agents.git
  16. Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.

    Stale GitHub, sofumel 8 ★MITUpdated 18 days ago

    git clone https://github.com/sofumel/claude-handoff-revive.git
  17. TraderHarness

    Datasets & benchmarks

    面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成,支持 A 股研究|Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data

    Indexed GitHub, HephaestLab 43 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/HephaestLab/TraderHarness.git
  18. Agent-Blackbox

    Tools & apps

    Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

    Stale GitHub, TaewoooPark 83 ★MITUpdated 14 days ago

    git clone https://github.com/TaewoooPark/Agent-Blackbox.git
  19. dsh-sieve

    Agents & frameworks

    dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

    Stale GitHub, Sev7eEn7 110 ★MITUpdated 15 days ago

    git clone https://github.com/Sev7eEn7/dsh-sieve.git
  20. dwarf_fortress_mcp

    MCP servers

    A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed semantic plans, evidence-backed effects, deterministic replay.

    Indexed GitHub, Dicklesworthstone 27 ★MITUpdated today

    git clone https://github.com/Dicklesworthstone/dwarf_fortress_mcp.git
  21. flow-map-resp

    Skills

    A Claude Code skill that turns your pipeline into an animated metro map, replayed from what a real run recorded. Retries as loop arcs, parallel work as rails, checks as hubs with spokes. React + SVG, your colours, light and dark.

    Stale GitHub, Galehashoid 69 ★Updated 11 days ago

    git clone https://github.com/Galehashoid/flow-map-resp.git
  22. Claude skills for NSE & BSE: scan, plan, replay 10,000x and size every Indian trade, with STT, circuit bands, the 3:15 closing auction and your broker's square-off built in. Paper by default.

    Stale GitHub, Adityaraj0421 8 ★MITUpdated 18 days ago

    git clone https://github.com/Adityaraj0421/dalal-street-skills.git
  23. FABULA-LLM-5

    Agents & frameworks

    A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.

    Stale GitHub, sergezuber 82 ★MITUpdated 55 days ago

    git clone https://github.com/sergezuber/FABULA-LLM-5.git
  24. flow-map-resp

    Skills

    A Claude Code skill that turns your pipeline into an animated metro map, replayed from what a real run recorded. Retries as loop arcs, parallel work as rails, checks as hubs with spokes. React + SVG, your colours, light and dark.

    Stale GitHub, Savagecount 32 ★Updated 19 days ago

    git clone https://github.com/Savagecount/flow-map-resp.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.