Library
87,246 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
code-guard-mcp
MCP serversSecurity scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.
@mlawsonking/code-guard-mcp@1.3.0 -
Covenant Guard
MCP serversHard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.
https://github.com/open-covenant/covenant/releases/download/covguard-v0.1.1/covenant-guard.mcpb@0.1.1 -
Stack Guardian
MCP servers14 checks, one command, graded findings. A health doctor for a home AI stack.
stack-guardian@0.4.1 -
GuardRails-MCP
MCP serversLocal prompt regression tracker with six fictional cases and evidence for human review.
guardrails-mcp@0.1.1 -
ci-guard-mcp
MCP serversLocal-first static repository security and configuration drift auditor (CLI, GitHub Action & MCP).
ci-guard-mcp@0.1.0 -
OPNsense Guard
MCP serversSafety-first OPNsense firewall MCP: read-only by default, planned and auto-reverting writes.
opnsense-guard-mcp@0.1.1 -
Spend Guard
MCP serversBudgets, payee allowlists, price-spike checks and human approval for agents paying x402 paywalls
@vulinh1704/spend-guard@0.2.0 -
SLF Guardian
MCP serversSafety checks an agent runs before it acts: packages, commands, prompt injection, links, code.
slf-guardian-mcp@1.2.0 -
ExceedLoop Guardcell
MCP serversSecurity scanning for code, containers and IaC: request scans, read findings, report fixes.
-
awesome-llm-observability
Prompts50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
git clone https://github.com/ContextJet-ai/awesome-llm-observability.git -
X3Guard-150M
Modelstext classification model by AxiomicLabs · transformers
AxiomicLabs/X3Guard-150M -
Security Guard Image Prompt
PromptsCreate an image of a Latino private security guard. The guard should be depicted wearing a tactical helmet and a bulletproof vest. The vest should have a communication radio attached and prominently display the word…
-
pilotfish
Agents & frameworksMulti-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
git clone https://github.com/Nanako0129/pilotfish.git -
agent-runtime-guard
MCP serversAgent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.
agent-runtime-guard@1.0.0 -
LeakRank Guard
MCP serversScans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
leakrank-guard@0.2.3 -
contract-guard-mcp
MCP serversEVM contract/token risk check + ERC20 approval (proxy, EIP-7702, unlimited-allowance). Zero deps.
ghcr.io/eltociear/contract-guard-mcp:mcp-1.1.0 -
guardvibe
MCP serversDeterministic security layer your AI can't be. 673 rules, 39 tools, CLI + doctor + host audit.
guardvibe@3.78.0 -
Guarded WhatsApp
MCP serversSecurity gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log.
guarded-whatsapp-mcp@0.1.0 -
agent-guardrail
MCP serversDeterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
guardrail-mcp@1.0.2 -
XRPL Token Guard
MCP serversRead-only XRP Ledger token-risk, issuer-authenticity and wallet-security checks.
-
fbc-guard
MCP serversStatic checks for Meta _fbc, _fbp and fbclid code that cause modified click ID warnings.
mcp-server-fbc-guard@0.1.0 -
Clotr Guard
MCP serversChecks text for credentials and personal details on your device; makes no network calls.
clotr-guard@0.1.3 -
agentic-os
PromptsGovernance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
git clone https://github.com/KbWen/agentic-os.git -
steve-guard
MCP serversOn-chain alpha data for trading agents: smart-money flow, wallet informedness, convergence, VPIN
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.