Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
Agnes-2.5-Pro-Theta
Modelsimage text to text model by Agnes-AI · transformers
Agnes-AI/Agnes-2.5-Pro-Theta -
agentlint
Agents & frameworksLocal guardrails for AI coding agents. Check proposed file changes and shell commands, block risky patterns, and return actionable feedback. Works with Claude Code, Codex, Cursor, Gemini CLI, and more
git clone https://github.com/mauhpr/agentlint.git -
Safeguard
MCP serversSoftware supply chain security: SBOMs, vulnerabilities, fixes, policies and compliance data.
-
dsh-auto-review
Agents & frameworksSecond-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
git clone https://github.com/PerryLink/dsh-auto-review.git -
x402-payment-safety
MCP serversAuthorize x402 payments before signing with request-bound, signed safety decisions.
-
Execute ai-safety-incident-logger-mcp
MCP serversPremium agentic endpoint for ai-safety-incident-logger-mcp.
-
OpenFDA Safety Data
MCP serversSearch FDA safety data: drug adverse events, recalls, and device events.
-
SafeStreets
MCP serversWalkability and pedestrian safety for any US address: scores, neighborhoods, deadly roads.
-
dwarf_fortress_mcp
MCP serversA 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.
git clone https://github.com/Dicklesworthstone/dwarf_fortress_mcp.git -
template-repo
Agents & frameworksAgent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
git clone https://github.com/AndrewAltimit/template-repo.git -
autorun
SkillsClaude Code & codex plugin + Gemini cli extension to keep ai running, keep data safe, plan better, and keep running until tasks are done.
git clone https://github.com/ahundt/autorun.git -
typo3-mcp-server
MCP serversOne MCP endpoint connects your TYPO3 site to Claude, Cursor, n8n, and any AI tool — safely through workspaces.
git clone https://github.com/hauptsacheNet/typo3-mcp-server.git -
SafeDep Vet MCP
MCP serversProtect your AI agents and IDEs from malicious open-source packages.
ghcr.io/safedep/vet:v1.20.0 -
granite-4.1-8b-llmon-preview
Modelstext generation model by ibm-granite · transformers
ibm-granite/granite-4.1-8b-llmon-preview -
uk-food-safety
MCP serversUK food safety and traceability — direct sales, labelling, raw milk, HACCP
-
saferagenticai-mcp
MCP serversRead-only tools over the Safer Agentic AI framework: 239 patterns + 15 heuristics.
saferagenticai-mcp@0.4.2 -
safe-fetch
MCP serversMCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.
safe-fetch-mcp-server@0.6.1 -
onchain-safety-mcp
MCP serversToken-safety for AI agents: rug/honeypot verdict + score across PulseChain, Monad, Base & BSC
@wickpics/onchain-safety-mcp@0.2.0 -
MCP Safety Warden
MCP serversMCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
mcpsafetywarden@1.7.8 -
food-safety
MCP serversFood additive safety: JECFA, EFSA, ADI, halal/kosher/vegan. 6K+ additives. Free.
-
Agent Safe
MCP serversEmail safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
-
FabTally Safe
MCP serversRead-only crypto safety: token honeypot checks, EIP-712 signature decode, approval scans.
-
GenPark Safe Eval Expression AST Sandbox
MCP serversZero-dependency AST safe mathematical and boolean expression evaluator and validator
https://github.com/Alpha-Park/genpark-safe-eval-expression-ast-sandbox-skill/releases/download/v1.0.1/genpark-safe-eval-expression-ast-sandbox-skill-v1.0.1.mcpb -
Safefood 360 MCP by usefulapi
MCP serversRead Safefood 360 documents, complaints, suppliers, materials; create complaints, update documents.
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.