Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Jixu
Agents & frameworksDurable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.
git clone https://github.com/joe960913/Jixu.git -
OpenMayhem
MCP serversUse OpenMayhem text, embedding and media models with explicit cost controls.
https://github.com/Trac-Systems/openmayhem-mcp/releases/download/v1.0.0/openmayhem-mcp-v1.0.0.mcpb -
EnvelopeBudget
MCP serversReview EnvelopeBudget data and optionally categorize transactions with explicit scoped permissions.
-
Ariadne
MCP serversLocal-first agent memory with verified backup rotation and explicit project isolation.
https://github.com/mclaut/ariadne/releases/download/v0.8.26/ariadne-v0.8.26.mcpb@0.8.26 -
Tvijo DSHREM
MCP serversPre-merge diff review and cloud assistance with explicit Tvijo spending limits.
tvijo-dshrem-mcp@0.2.1 -
open-genjutsu
AI repositoriesLocal-first AI video recasting with draft review, explicit HD approval, and source-audio restoration.
git clone https://github.com/Anil-matcha/open-genjutsu.git -
Staticbot
MCP serversDeploy websites, migrate app backends, and run continuous sync with explicit approval gates.
@staticbot/mcp@1.8.2 -
Qdrant Memory
MCP serversPersistent scoped Qdrant memory for agents, through four explicit stdio MCP tools.
qdrant-memory-mcp@0.3.5 -
Checktrail
MCP serversLocal code validation with explicit execution trust and evidence of what actually ran.
@stsepelin/checktrail@0.1.0-alpha.5 -
kali-mcp-go
MCP serversMCP runtime for AI-assisted security testing with Kali tools, explicit target controls, bounded scanning, structured evidence, and persistent Docker deployment.
git clone https://github.com/found-cake/kali-mcp-go.git -
claude-blog
SkillsFree, open source blog writer for Claude Code. Researches current sources, writes answer-first posts for Google and AI answers, has an independent reviewer score each one out of 100 and ships only after five delivery gates. 32 skills, 30 /blog commands, 5 agents. Active development at AI-Marketing-Hub/claude-blog; public releases ship here.
git clone https://github.com/AgriciDaniel/claude-blog.git -
self-media-content-workflow
SkillsModular, tool-agnostic agent skills for social media content: briefs, trend research, platform-native copy for Xiaohongshu, WeChat, X and YouTube, short video, publishing, and analytics.
git clone https://github.com/yanhua1010/self-media-content-workflow.git -
LevelRoam
MCP serversRead-only game, setup, place, evidence and travel decision tools with explicit provenance.
-
MEO Preflight
MCP serversRead-only machine payment preflight using dated MEO evidence, with explicit unknowns.
-
ownership-attestation-protocol
MCP serversMCP protocol enforcing explicit task acceptance and attestation-tagged completion claims.
-
Esheria Regulatory Intelligence
MCP serversCitation-backed regulatory intelligence tools for explicit multi-jurisdiction packs
esheria@1.2.2 -
SuperPost
MCP serversSocial MCP for ideas, unscheduled drafts, review proposals, scheduling, and explicit publishing.
-
Outbound OS
MCP serversEvidence-gated email outreach MCP with dry-run defaults and explicit send approvals.
ghcr.io/recepiohq/outbound-os-mcp:0.2.1 -
Coral
MCP serversPrivate, non-explicit intimacy exercises, scripts and a couples quiz for adults 18+.
-
claude-content-skills
SkillsFree, copy-paste Claude skills that run your content growth factory — turn ideas + your NotebookLM memory into scroll-stopping Instagram reels. By Ootto.
git clone https://github.com/Ootto-AI/claude-content-skills.git -
x-reader
MCP serversUniversal content reader MCP Server for 10+ platforms
git clone https://github.com/runesleo/x-reader.git -
Cocuyo
MCP serversQuote and create AI images and videos with existing Cocuyo credits and explicit confirmation.
-
mcpie
MCP serversStanding-order Domino's pizza button: dry-run freely, order on explicit confirm. Cash default.
mcpie-pizza@0.2.0 -
srdcheck
MCP serversScoped deterministic SRD 5.2.1 rules checks for agents — applied rules cited, boundaries explicit.
srdcheck@0.8.0
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.