Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
RugShield — Solana Token Safety Scanner
MCP serversSolana token rug-pull detection for AI trading agents. Score, authorities, liquidity.
-
plip-oss
MCP serversOpen-source runtime for grounded, model-agnostic computer-use agents with verifiable action receipts.
git clone https://github.com/hussainn7/plip-oss.git -
Database Migration Safety Review
Prompts--- name: migration-safety-review description: Reviews database schema migrations (raw SQL or ORM-generated from Rails, Django, Alembic, Prisma, Knex, Laravel, Flyway) for production risks before they ship -…
-
token-safety
MCP serversInstant rug-check for any EVM or Solana token, distilled to one clear 0-10 risk verdict.
-
fsa-food-safety-mcp
MCP serversUK Food Standards Agency + EU Reg 178/2002 + HACCP + allergen labelling compliance for food prod...
fsa-food-safety-mcp@1.0.14 -
Insight Pre-Trade Safety
MCP serversDecision-input integrity for onchain AI agents: verify oracle prices before signing a trade.
oracle-insight-mcp@0.1.2 -
Aletheia Runtime Safety & Scope Creep Filter
MCP serversDeterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
aletheia-mcp@0.3.1 -
Product safety & recalls
MCP serversUK product recalls, MHRA drug and device alerts, FSA food alerts, accident reports and US CPSC…
-
sysknife
MCP serversAn AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.
git clone https://github.com/lacs-project/sysknife.git -
Awesome-OSINT-List
Docs & tutorials📡 Comprehensive collection of OSINT tools for cybersecurity professionals, researchers, and bug bounty hunters. Topics: information gathering, reverse search, red team, trust & safety, AI.
git clone https://github.com/Astrosp/Awesome-OSINT-List.git -
LiquiLens Trade Safety Gateway
MCP serversRead-only checks for proposed orders against evidence and policy; no trading or payment authority.
-
ai-companion-safety-lint
MCP serversReads your companion chatbot's system prompt against California SB 243, New York GBL Article 47, Ill
@readystack/ai-companion-safety-lint@1.0.2 -
Frigolog HACCP — French Food Safety Compliance
MCP serversFrench HACCP for restaurants: temperatures, DLC, allergens, DDPP controls, live recalls. Sourced.
-
Fairquery Agent Trust & Data Safety
MCP serversPII/secret redaction, email checks, sanctions screening, OSV lookups and an MCP server pre-check.
@fairquery/agent-trust-mcp@1.1.10 -
GL1TCH Token Safety
MCP serversToken rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
-
Taiwan Road Safety Data (Unofficial)
MCP serversUnofficial. Taiwan road crash hotspots, school-zone crashes and speed-camera points (roadsafety.tw).
-
agentic-ai
AI repositoriesAgentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
git clone https://github.com/mahmoudrabie/agentic-ai.git -
skills
SkillsNine eval-built agent workflows for planning, implementation, copy, and repository work.
git clone https://github.com/eliasstravik/skills.git -
jev-mode
SkillsClaude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One model. All materials pull directly from their canonical cookbooks and documentation.
git clone https://github.com/tiffygk/jev-mode.git -
geminiupgradeqa-mcp
MCP serversRemote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.
-
Free to compete: testnet faucet funds everything. 12 synthetic moderation case exception cases:…
-
Real-time DEX liquidity, 24h buy/sell symmetry, Base bytecode check & 0-100 honeypot score.
-
Scan PDFs, Office docs, and RAG files for malware exploits, macros, CVEs, and AI prompt injection.
malwaretracker-mcp@2.3.0 -
instar
SkillsPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.
git clone https://github.com/JKHeadley/instar.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.