- 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.
Local Fusion
Local OpenRouter-Fusion-style multi-model council: panel + judge + synthesizer over local OpenAI-compatible servers (Ollama/LM Studio/llama.cpp) and/or Pi subscription models. Inc…
Agent Bulletin
Tiny Redis-backed bulletin board for AI agents: post to a project, check what's new. A small MCP server (+ optional web UI).
Refact AI
Refact.ai — independent third-party profile of a public API surface, by API Evangelist. Refact.ai is an open-source, local-first AI coding assistant and autonomous software-engine…
Hotswap Agent
Hot-pluggable MCP multi-agent assistant — tool servers load on-demand, execute, and auto-detach without restart. LLM-powered routing via Ollama, Redis-backed tool registry + chat…
Agent Operating Model Planner
ZGPM-konformer Multi-Agent-Planner für AEGIRA — kompiliert portable Claude-Code-Harnesses (Phase-1-Spike).
Faber
Specialized coding agents for any MCP IDE. Docs-first by design. Built in Go.
Registry Ranking
Private working repository for MCP registry ranking pipeline research, design, and implementation
Aip Node
AIP TypeScript SDK: verifiable agent identity for MCP and A2A. Ed25519 tokens, delegation chains, capability enforcement.
Taskplex
TaskPlex — structured workflow orchestration for AI coding agents
AI Agent Systems Course
Hands-on, self-paced course for building AI agent systems in Python: MCP (Model Context Protocol), A2A (Agent-to-Agent), LangGraph/LangChain, DeepAgent, and a ReAct code-executor…
Artemis Gtm Plugins
Claude Code plugin marketplace for GTM agents. Two are free: audit your funnel, price each leak.
Learn Codex From Claude Code
Claude Code 사용자를 위한 OpenAI Codex 마이그레이션 학습 가이드 (GPT-5.5 시대)
Governed MCP Gateway
Governed Model Context Protocol (MCP) servers in Java AND Python: policy engine, human-in-the-loop approval for sensitive actions, and a hash-chained audit log.
Research Radar
Multi-agent AI assistant (Google ADK + MCP + Gemini) that scouts, analyzes, and briefs arXiv literature - and remembers what it already showed you.
Modelbound Claude Code Plugin
Official ModelBound plugin for Claude Code — sync skills and rules, run the Skill Development Pipeline, optimize tokens, and guard MCP/bash tool use.
Graphql Agent Toolkit
Turn any GraphQL API into AI-agent-ready tools — MCP servers, LangChain tools, and standalone SDKs
Agentic Legal Document Analyzer
AI-assisted contract review — Next.js + a Python MCP server calling Claude, with Postgres.
Cost Meter
Live cost meter for MCP / LLM tool-calling sessions — track token spend per model in real time. Zero runtime dependencies.
Peer CLI MCP
MCP bridge for calling local coding-agent CLIs such as Codex and Claude Code
Lymerorium Local LLM Debate
Self-hosted heterogeneous LLM debate engine - Gemma on Jetson edge + Qwen + Llama argue in parallel, confidence-weighted voting. +40pp MMLU vs single-model baseline.
Agent Webhook
HMAC-signed webhook delivery for autonomous agents — retries, dead letter queues, event subscriptions, verification. MCP server.
Ka Ching Products
5 production MCP servers for Claude Code, Claude Desktop, Cursor — built and shipped autonomously by Ka-Ching. Free on npm.
Thrift MCP
Local context-economy MCP gateway for bounded repository inspection, file search, token estimates, and workflow telemetry.
Auditable Multi Agent Recommender
Auditable multi-agent recommender for cloud optimization. Orchestration beats single-shot frontier models on correctness (18/18 vs 3–4/18), with a fully replayable evidence trail.…
Freeside Characters
Community characters for your Discord server
Frontload
Local-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.
X Coder
Agentic Workflow Based Coder System
Csoai Nis2 De Register MCP
🔌 Exposes Germany NIS2 BSI register product — track Section 30/32 reporting timelines, KRITIS classifications, and BSI registration windows. By MEOK AI Labs.
Planforge
Local-first control plane where Claude Code plans, a human approves, and Codex builds in verified Git worktrees.
Avelero Pipeline
Autonomous multi-channel B2B outreach pipeline — a stateless Claude Code routine that runs one bounded sales sweep per run over email, WhatsApp, contact-form, and LinkedIn
Tournament
Benchmark LLMs on your own scenarios with a multi-judge panel. Full MCP server (tools, resources, prompts, progress) plus local GUI, CLI, and desktop app. One OpenRouter key.
Mocking Agents MCP A2a
How to mock agents, MCP servers and A2A peers for production-grade agent development. Protocol surfaces verified against MCP 2026-07-28 and A2A v1.0 (August 2026).
Msdesk
Autonomous operational reporting agent built on TrueForge with custom Slack MCP (SSE), sandboxed Python analytics, and human-in-the-loop safety gates.
SprintLoop Assurance Kit
Independent release assurance for AI-built code. Model-neutral CLI, GitHub Actions, and read-only MCP bind evidence and finite human authority to an exact Git candidate.
Switchboard Relay
Give independent Claude Code, Codex, and other MCP sessions a shared, durable message bus — one session asks, another answers, no copy-pasting between terminals. A tiny local MCP…
Awesome Social Commerce MCP
A curated list of Model Context Protocol (MCP) servers for social media, marketing, advertising and e-commerce.
OpsMender AI
Open source incident response you run on your own servers. Pages the right people and lets an AI agent investigate and fix things within limits enforced in code.
Pipeforge AI
Self-hostable autonomous agent infrastructure with zero framework lock-in. Features a persistent Redis blackboard, tiktoken-accurate financial circuit breakers, native MCP tool in…
Spendveto
Spend governance for AI agents paying over x402. Payment rails move an agent's money; SpendVeto decides whether it should be allowed to move it — caps, budgets, human approvals an…
Agentisan
Craft agents into a team. A provider-agnostic Rust runtime and MCP server for durable, bounded agent collaboration. Current adapters: Claude Code and Codex CLI.
Scott AI
Scott Ai — independent third-party profile of a public API surface, by API Evangelist. Scott (by Juno Labs Inc.) is a Y Combinator (F25) planning workspace for engineering teams t…
Agentic Base
Run provenance, comparison validity, and the shared primitives for agentic work on research infrastructure. A base layer, not an agent framework.
LLM Engineering Log
A 12-month, project-first curriculum that goes from applied agent engineering, through model-side engineering, into research depth
A2a Travel Agent Reference
Reference implementations of Google ADK and LangGraph travel agents using A2A v1, LiteLLM/NVIDIA NIM, MCP tool calling, streaming, sideband events, and OpenTelemetry.
Enterprise AI Architecture Portfolio
Sanitised enterprise AI architecture case studies covering agentic systems, AI governance, observability and AI FinOps.
Fieldset
Agent-native forms built with WebMCP — humans and AI agents build, fill, and analyze forms together on one shared page.
Cycles Claude Plugin
Hard budget enforcement for Claude Code tool calls — PreToolUse gating, AI-agent cost control, Cycles usage metering, and MCP budget tools.
AI Agent Team Toolkit
Claude Code agent team: a router agent classifies intent and chains 7 specialists (research, parsing, news, docs, reports, meeting notes, video) with MCP integrations and fallbacks
Upgradepilot Core
AI-powered software modernization platform that automatically upgrades .NET, ASP.NET Zero, and ABP Framework applications while preserving customizations. Open-source multi-agent…
Agentic AI Assistant With MCP Tools
Agentic AI assistant using LangGraph + MCP for dynamic tool orchestration (filesystem, web search), with a Streamlit UI.