Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
bifrost
MCP serversOpen-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
git clone https://github.com/maximhq/bifrost.git -
mcp-audit-tool
MCP servers🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.
git clone https://github.com/graygnatconsole/mcp-audit-tool.git -
arifOS
MCP serversIndependent policy kernel for AI agents: judge before execute. F1–F13 floors, VAULT999 receipts. Not a model. Not a chatbot.
git clone https://github.com/ariffazil/arifOS.git -
End-to-End-Agentic-Ai-Automation-Lab
MCP serversThis repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.
git clone https://github.com/MDalamin5/End-to-End-Agentic-Ai-Automation-Lab.git -
ThumbGate
MCP serversThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
git clone https://github.com/IgorGanapolsky/ThumbGate.git -
agentpay-sentinel-mcp
MCP serversSecurity guardrails for AI agent payments
-
spotdb
MCP serversEphemeral data sandbox for AI workflows with guardrails and security
docker.io/aliengiraffe/spotdb:0.1.0 -
Stratum MCP
MCP serversStructured execution for coding agents: contracts, postconditions, gates, guardrails.
@smartmemory/stratum@0.7.3 -
agent-guard
MCP serversConstitutional guardrails and loop detection for AI agents
agent-guard-mcp@0.1.3 -
Stratum MCP
MCP serversStructured execution for Claude Code — contracts, postconditions, gates, guardrails.
stratum-mcp@0.2.42 -
pitbridge
MCP serversLocal-first MCP bridge for NinjaTrader 8 behind a deterministic guardrail engine.
pitbridge@0.2.2 -
Aegis Policy
MCP serversGovernance firewall and safety guardrails oracle for AI swarms.
-
Kinocut
MCP serversGuardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.
kinocut@2.0.1 -
superuser
MCP serversPermission-gated superuser (sysadmin) MCP agent with enterprise guardrails and audit.
superuser@0.1.1 -
aidimag
MCP serversPersistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
aidimag@1.0.22 -
Oi
MCP serversAccess Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.
-
mandateguard
MCP serversDeterministic payment policy guardrail for AI agents - budgets, allowlists, signed mandates.
https://github.com/ezequiellich44-cmd/MandateGuard/releases/download/v1.1.0/mandateguard-1.0.0.mcpb -
kubeleash
MCP serversKubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.
ghcr.io/kubeleash/kubeleash:0.3.0 -
memini
MCP serversLocal-first project memory and mistake-prevention guardrails for AI coding agents.
memini@0.4.0 -
Anchord (AnchorID)
MCP serversRead-only MCP for identity resolution and write guardrails.
@anchord/mcp-server@1.1.1 -
zenable
MCP serversZenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails
-
creedspace-mcp-server
MCP serversConstitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
@creedspace/mcp-server@1.1.4 -
aidimag
MCP serversPersistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
aidimag@1.0.20 -
guard
MCP serversLocal-first architecture guardrails and project context for JS/TS AI coding agents.
@codapult/guard@0.14.1
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.