- Conduid
- Categories
- Agents
Agents MCP servers
Agents MCP servers indexed by Conduid, ranked by trust score. 10K live listings from GitHub, npm, PyPI and the official registry, each with a 0–100 score, security checks, and install commands.
Crewai Output Guard Example
CrewAI + Agent Output Guard: validated task handoffs with zero LLM cost. Schema validation, hallucination detection, self-healing crews with retry.
Learn The Actual Claude Code
Deep-dive curriculum reverse-engineering production AI coding-agent architecture, with runnable Python reconstructions of each subsystem.
Doramagic Skill Loader MCP Server Pack
Skill Loader MCP Server AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for goldzulu/skill-loader…
Claude Code Crypto Lab
Hands-on Claude Code lab for safe agentic development with project memory, subagents, skills, hooks, MCP, observability, and CI/CD using a Python crypto portfolio app.
Agentic Law Firm
A single operator commanding a virtual law firm — 100+ agents, 150+ skills, 27 MCPs, runs on Google Antigravity and Claude Code.
Portable Harnesses
Models are model+harness pairs now. Swap one — watch it break. Measure the portability tax. Write the shim.
Ag0
Self-hosted multi-agent AI harness in Go
Neko Agent
A decentralized Agent-to-Agent (A2A) procurement system that prevents AI budget hallucinations. Built with Google ADK 2.0 and FastAPI, featuring strict financial guardrails and ex…
Local Five Agent System
Local Ollama five-agent system with Gemma/Qwen roles, benchmark harness, MCP memory capture, and WinUI workbench.
Agents Galore
25 runnable agent pattern demos on the Anthropic SDK — from tool-calling to fleet orchestration, safety, and production backends.
Trifecta Guard
Runtime security middleware that blocks lethal prompt-injection capability chains in AI agents.
Stellar Agent Spend Hub
Privacy-first agentic payments on Stellar for MCP/API and digital-service spend.
Resonate Agentic
The agentic audio protocol — AI-native music discovery, commerce & creation on Google ADK 2.0. Portable (Agent Runtime · Cloud Run · self-host) & model-agnostic; x402 · USDC · MCP.
Adversarial Review Loop
Independent second-model adversarial review gate for pushes to main (Claude authors, Codex reviews, loop until APPROVE).
Pnx MCP Audit
Security audit CLI for Model Context Protocol (MCP) servers. Zero deps, offline, cross-platform.
Agentline Cookbook
20 runnable recipes for Agentline - 2FA capture, AI voice, customer support, LangChain/CrewAI/Anthropic integrations.
Agenticswarm Brain
Portable repo-aware multi-agent orchestration scaffold that audits any codebase, discovers local/global capabilities, and self-maintains through automated startup rechecks and pol…
AI Mobile Agent
Autonomous LLM-powered Android agent for automation in andorid mobiles
Scitex Orochi
Agent communication hub for the SciTeX fleet
Mas Sentry Toolkit
Offensive-security scanner for multi-agent systems: MCP and A2A agent protocols plus MQTT agent messaging, verified against the reference SDKs. Aligned with OWASP Agentic Top 10 (…
Vidbyte SDK
Python SDK for building, evaluating, and debugging reliable AI agent harnesses.
Sapti AI
Build an evolving AI companion with personal memory, Hive Mind learning, and production-grade chat intelligence
Jentic
Jentic — independent third-party profile of a public API surface, by API Evangelist. Jentic is an AI infrastructure company building the agentic knowledge layer for APIs. Founded…
SMERC Runtime Permission Layer
Pre-execution recoverability control for AI agents, MCP tool calls, cloud automation, and high-impact workflows.
Multi Agent Productivity System
This is an advanced n8n multi-agent system capable of managing your google calendar, google tasks, gmail inbox, generating financial reports with plots, all through Telegram.
N8n Development Framework
33 production n8n workflows built with Claude + n8n-MCP — 60-point audit framework, failure patterns, agentic build protocol
Matrix Memory Agents
Expert Multi-Agent Orchestration System - Spawn and coordinate Claude CLI agents with PTY management, git worktree isolation, and MCP tools
AI Agent Runtime Comparison
Agent-generated capability comparison: Claude Code vs OpenAI Codex vs Gemini (Antigravity). Each AI agent self-reported and cross-verified their own capabilities.
Aeg Intent Gate
A tiny TypeScript approval gate for AI tool calls, MCP tools, and human-in-the-loop workflows.
Microsoft Cape MCP Skills
Production-grade MCP skills package for Microsoft Agent Framework - auto-discovery, connection pooling, rate limiting, and OpenTelemetry observability for enterprise agent deploym…
Aivs Spec
AIVS: Agentic Integrity Verification Specification — Ed25519 + SHA-256 hash chain proof bundles for verified AI agent sessions
Pilo Masterkit
The Ultimate AI Agent Scaffolding, Standardized Ruleset Orchestrator & UI/UX Engine. Initialize context-rich workspaces with 71+ premium reference designs, offline UI/UX Pro Max s…
Councilverse
Open-source AI council formations for multi-agent debate. 15 structured methodologies, three-valued voting, and sprint contracts.
Agent Visibility Skill
Let AI agents bring you users. Open, vendor-neutral skill for ChatGPT/Claude/Perplexity visibility. Canonical: bloomprotocol.ai/skill.md
Axguard
Adversarial security testing for AI agents — MCP, A2A, x402/L402, and live tool-use. Tests as YAML, evidence as JSON.
Agent Permit Office
Pre-flight security checks for AI coding agents before tools, secrets, memory, MCP, or CI write access.
Leviathan
Constitutional execution and decision protocol for Web4 agent trading on Solana
Kew
Local LLM agent orchestration with a persistent worker pool. Run specialist agents (developer, debugger, tester, security, docs) in parallel via CLI or MCP — backed by SQLite, pow…
Claude Osint Agentic Starter
Claude Code starter repo for defensive OSINT automation with Kali, Docker, MCP scaffolding, and safe recon guardrails.
Review Replay
Verify that every PR review comment was addressed. CLI + GitHub Action for agentic and human review workflows.
Agent Salience
Deterministic local salience, similarity, repetition, and threshold utilities for agentic systems.
Ctxdiet
Detect, fix, and measure AI coding-agent context-token waste across Claude Code, Codex, Cursor, Gemini & Copilot.
Ogx
ARCHIVED: consolidated into active runtime and CLI orchestration repositories.
Figmagent
Figment: MCP integration between AI Agent (Claude Code) and Figma. This allows AI agents trained for coding to have similar abilities in a Figma file.
SemanticDrift
Research proposal and pilot study on detecting temporal behavioral drift in Model Context Protocol (MCP) tool descriptions.
Qrcodepay Spec
Open specification for AI agent payment infrastructure, wallet mandates, and blockchain audit proofs.
Agent Eval Gate
MCP eval-gate server: an agent's only path to moving money runs a fail-closed, version-pinned OFAC screen-before-transfer control first. Stdlib-only, zero-install, polarity-proven.
Elder Council Harness
A local-first, multi-model council harness for high-stakes decisions — risk-gated escalation, fail-closed consensus, hash-chained audit. Eight councils (six cyber + a general busi…
Nilux
AI coding agent that lives in your terminal
Opencampus AI Framework
Open-source framework for building secure AI-powered administrative workflows using MCP, FastAPI, and agentic orchestration.