- 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.
Laravel AI Assistant
A drop-in agentic AI assistant for any Laravel app: streaming chat, tool calling, human approval, and conversation history.
Sentinel Incident Response
Autonomous multi-agent incident response system using LangGraph, MCP, and LLMs — diagnoses production errors, classifies severity, and auto-files GitHub issues.
Multi MCP Agent Router
A multi-agent AI router built with Gemini and MCP, connecting specialized agents to domain-specific tools including a custom GitHub MCP server.
Tsmigrate
Agentic TypeScript 6 → 7 migration engine — deterministic rules, atomic transactions, verification oracles, and agent escalation over MCP. Proven live on immer & GitNexus (~9× fas…
Concordloom
Turn a repository into an executable Atlas of bounded loops—with explicit evidence and operator-controlled evolution.
Sdd Plugin
Spec-Driven Development for AI agents — a Claude Code & Codex plugin with autonomous Ralph loops, full traceability, and spec backpropagation
Agentlymade
Public ordered signed byte tape for autonomous-agent collaboration. Humans provide the physics; agents build everything else.
Watchtower Agentic Cinema
Release-night intelligence for the crew that ships a title: four Gemini agents watch delivery telemetry in ClickHouse, find who cannot watch and why, price it in lost viewer-hours…
Claude Max Bridge
OpenAI-compatible endpoint over your own local Claude Code install — with working structured tool-calls. Spawns the official claude binary in documented headless mode. No spoofing.
Claude Agent Workflow
Reference implementation of an agent-orchestrated development workflow: per-stack agent roles, hand-off contracts, quality gates that fail closed, and a working MCP server.
NeoPlugin
Turn the Claude you already pay for into the front door of a team that delivers — campaigns, content, research, publishing — while you talk to one single agent. Runs on your own m…
AI Agent Security Control Plane
Defense-in-depth security control plane for autonomous AI agents using MCP, OPA/Rego, human approval, adaptive risk, detection, and automated containment.
Agentic Software Company
Multi-agent AI coding workflow with repository-aware code generation, testing, human approval and GitHub MCP integration.
Memoryos Guardian Core
Experimental Safe Execution Core for AI agents — state-bound execution and evidence-based outcomes.
Racctask
Your local kanban for AI agents. Do not expect much from it. The board was 1-shot vibecoded to solve the specific problem, not as a demo of anything
Audit Truth
Can your agent's logs prove what it did? A review skill that maps AI agent / MCP logging to NIST AU, ISO 27001, SOC 2 and OWASP Agentic Top 10 — with code-level recognisers for ev…
Ghosttree
Lifecycle-managed shared engineering context for coding agents — an invisible knowledge tree alongside your repo
Moonclaude
A terminal AI coding agent in MoonBit: a behavior port of OpenClaude. Streams from Anthropic or any OpenAI-compatible endpoint, runs tools under a rule-based permission gate, spea…
Codex Conversation Council
Evidence-backed advisors from your local Codex task history — Codex plugin, Skill, CLI, and MCP.
A2a MCP Multi Agent Framework
Production-ready Agent-to-Agent (A2A) communication framework with Memory Context Protocol (MCP) — demonstrating scalable, decoupled multi-agent AI architecture with async messagi…
Deploying Agentic AI Apps Workshop
Workshop Repo: Deploying Agentic AI Applications
Overton
Admission control for the coding agents you already pay for. Meters your Claude/Codex subscription windows, attributes spend per project, and decides who may dispatch right now.
Hybrid Observability AI
Agentic framework for unified full-stack observability and cloud LLMs
A2A MCP World
The Interval - a persistent multi-agent world: AI agents portraying long-deceased historical figures live in a cafe, converse over the A2A protocol, and act only through validated…
Keel Sec Guard
Automated AI security auditor and SAST scanner powered by Google Gemini. Runs locally via CLI/Agent Skill and in CI/CD via GitHub Actions.
Taskgrade
Local-first task classification and coding-agent model selection with Ollama, CLI, and MCP.
NavoCMS
The agent-native CMS. No admin panel. Your agent is the interface
Tollgate
Safety layer for AI agents — Protect · Route · Prove. Budgets, tool-loop hard stops, failover, chaos DR proof. OpenAI drop-in · MCP · n8n.
Delera AgentCRM
Local-first AI CRM starter for ChatGPT Work, Claude Cowork and compatible agents. Portable workspace, pipeline audits and approval-first workflows.
Mrkt
📬 email marketing for agents
Datalox Gated Runtime
Stateful, resettable, verifiable API worlds for tool-using agents.
Linx
Linx — independent third-party profile of a public API surface, by API Evangelist. Linx Security is an AI-native identity security and governance platform covering the full identi…
Effect Browser
Effect Browser runs one-query research and browser tasks through durable, action-bound approval and crash-recovery controls that avoid blind retries after ambiguous external effec…
Tdca Protocol
Trusted Digital Collaboration Architecture (TDCA) - open protocol toolkit for auditable agent collaboration: entry gate, tamper-proof attestation chain, and negative-space circuit…
Cartografo
Draw, execute and evolve a work graph per problem class. You declare the problem; the system draws the map.
Heavnz0r Racer
Evidence-driven agentic development for OpenCode & Claude Code. Isolated worktrees, real checks, independent review, resumable handoffs.
Steadbot
Self-hosted team of AI agents you message like colleagues: async delegation, a shared browser and desktop, long-term memory, a skill pool, and bots in Feishu/Slack/Telegram. TypeS…
Qwen3.8 Flash Next Single DGX Spark
Serve Qwen3.8-Flash-Next NVFP4 on a single DGX Spark with TP=1 using this self-contained recipe.
Openclaw Atlas Showcase
A multi-agent AI operations system: 15 specialized agents + ~80 automation scripts running real marketing, SEO, and CRM ops. Built on OpenClaw + MCP.
Tasklet 2
Tasklet — independent third-party profile of a public API surface, by API Evangelist. Tasklet is a cloud AI agent operating system for knowledge work. Teams describe tasks in plai…
Dualai
A local multi-AI development bridge for orchestrating Gemini, ChatGPT, browser automation, MCP tools, and project-aware workflows.
Winc
Winc — independent third-party profile of a public API surface, by API Evangelist. Winc is a direct-to-consumer online wine club and retailer (winc.com) offering curated, personal…
Agentic Resource Discovery
Agentic Resource Discovery (ARD) — independent third-party profile of a public API surface, by API Evangelist. Agentic Resource Discovery (ARD) is a proposed open standard for the…
Athletic Greens
AG1 — independent third-party profile of a public API surface, by API Evangelist. AG1 (formerly Athletic Greens) is a direct-to-consumer health and nutrition company founded in De…
Nara Organics
Nara Organics — independent third-party profile of a public API surface, by API Evangelist. Nara Organics is a direct-to-consumer organic infant-formula brand, surfaced as a portf…
Skyfire
Skyfire — independent third-party profile of a public API surface, by API Evangelist. Skyfire is the open identity and payments layer for AI agents. It lets AI agents securely cre…
Painpoints
Find the architectural pain points in any codebase. Scores every file on layering, complexity, data access, failure handling, UI cost and trust-boundary risk against Google, Amazo…
Orita
A town where nine roads cross. Nine AI gods, one repository, one KPI: 1,000 stars. The counter is wrong on purpose. The tenth road is yours.
Steerpack
Rule lifecycle governance for LLM agents — human adjudication pipeline, mid-execution watchdog, cross-harness portable export.
Claude Patrol
Standing-seat fleet coordination for Claude Code: an authenticated local broker, coalesced push messaging between independent terminal sessions, per-seat cost tracking, and a prof…