- Conduid
- Marketplace
- #ai-agents
MCP servers tagged ai-agents
15K live MCP servers tagged "ai-agents", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-agents.
Web Agent Gateway
Local least-authority gateway connecting Web AI clients to user-approved developer resources.
Agentmbx
AgentMBX: a signed mailbox for AI coding agents (Claude Code, Codex, OpenCode, Kimi, Hermes) on one machine and across your LAN, with idle-session wake-ups and verifiable owner au…
Agent Sessions MCP
MCP server for agent session lifecycle, persistent context, transcripts, and a human-gated memory-promotion pipeline - with an append-only audit trail
Understanding LLMs
Understanding LLMs for Software Engineers: a systems-first, bilingual guide to LLM principles, mechanisms, and boundaries.
Xcrap MCP
MCP server for XCrap: give Claude, Cursor and other agents read access to X (Twitter). Twelve read-only tools, no API key.
Hota MCP
MCP-сервер, через который ИИ-агент играет в Героев III: Horn of the Abyss как живой игрок — настоящие кнопки, наблюдения структурой без OCR, хотсит и команды, встроенный справочни…
Beijixing
企业级 零信任 Agent harness治理框架：统一准入、任务级最小授权、证据核验、预算、审批、审计、撤销与回滚。
Go Workflow
Standalone DAG workflow engine for Go — 15 step types, MCP integration, durable Postgres execution (SKIP LOCKED), templates, approvals, crash recovery
Codex Toolloop
Build agentic coding workflows with OpenAI Codex ToolLoop: Based on the Codex app-server and Vercel AI SDK v6, codex exec automation, JSONL events, structured outputs, dynamic too…
30 Days Of AI Agents
Build a new AI agent every day for 30 days. From zero to production multi-agent systems. LangGraph, CrewAI, OpenAI Agents SDK, Claude, MCP, A2A.
Webaudit
Evidence-first browser automation for AI agents and operators, with recovery and MCP.
Airlocked Agents
Deterministic IaC for a private, self-hosted AI automation stack — untrusted content stays in the airlock.
Caypo
Agent finance on institutional rails — MPP payments, USDCx transfers, MCP server, CLI
A Protocol
MCP-A -- the MCP Answers Profile: a specialization of MCP that returns compiled, precise, structured answers. v1.0-beta.
EcommAPI
Plataforma Python de automação de e-commerce — sincroniza estoque entre fornecedor e Bling ERP, com camada de IA (Claude/Gemini) para sugestões de preço sob aprovação humana via M…
AI Visibility
See how AI sees your brand. Scores, platform breakdowns, competitive benchmarks — for any domain, from your terminal.
Sre Harness
A minimal, runnable reference harness for SRE agents: tool orchestration, verification, memory, guardrails, and observability in one ~40-line loop. Agent = Model + Harness.
Promptweave
YAML composer for assembling agent prompts, hooks, and MCP configs
Openclaw Nie Guard
Cryptographic trust mediation layer for AI agent frameworks. Apache 2.0 reference architecture composing device-attested admission, short-TTL scoped capabilities, runtime continui…
Remembrance Skills
Open, reviewed skills + MCP for AI coding agents — verified, quality-gated memory that gets better instead of drifting.
Eugenio Agent Portfolio
Portfolio técnico de Eugenio Santiago — arquitetura de agentes AI: multi-agent systems, MCP servers, n8n workflows. Berlin.
Awesome MCP Workflows
Bilingual MCP catalog of workflow patterns, server shapes, and launchable combinations with explicit evidence levels.
LangValidator
Self validating LangGraph agent pipeline: every agent output passes through a checkpoint node that scores it and routes to pass, retry with feedback, or halt. Includes rule based,…
Workcell
Multi-agent operations platform for development projects — a human board directs; an AI team (Orchestrator/Developer/Designer/QA) ships with proof. Design-first, proof-gated. MIT,…
Claude Memory 3tier
Auto-activating 3-tier memory for Claude Code: per-repo markdown bank that survives /compact, + optional basic-memory (Obsidian) and CodeGraph layers.
Superclawd
Claude Code, supercharged — your team's standards, every session
Pre Sales Agent
Open-source starter for AI-powered pre-sales agents that turn RFPs and briefs into estimates, clarification loops, and proposal drafts.
Synara MCP
Cross-session memory for MCP agents — episodic + semantic, recall ranked by a successor-representation prior.
Codex Multi Agents Loop
Codex-native multi-agent engineering loop for software projects: structured evaluation, bounded iterations, SQLite state, artifacts, and project memory.
Macaroni
🍝 Macaroni — your Mac, at your command. A local MCP/CLI suite that bridges macOS apps (starting with Messages) to AI agents.
Synoppy MCP
Synoppy MCP server — give your AI agent the whole web. Read, crawl, map, extract, classify & enrich live pages from Claude, Cursor, or any MCP client.
100x Agent Toolkit
A production-grade engineering toolkit for AI-assisted software development. Contains 100 specialized skill workflows, 142 expert agent personas, 74 design system specifications,…
Wires
Give your agent tools on other machines as CLIs: callers identified by your IdP, an admin-signed service registry, hosts that can message the agent back, dial-by-key over iroh. Ex…
Codex Quiet Clock
Local Codex time-awareness extension: prompt hook + read-only MCP for thread timelines, elapsed time, and date-boundary context.
Maxwells Defense
Adaptive proof-of-work defense for AI agents. Asymmetric thermodynamic cost: attackers dissipate, defenders verify in O(1). Reference implementation of T-IB-09 (Adversarial Dissip…
Aidememo
Local-first memory for coding agents: typed facts, knowledge graphs, temporal history, MCP, SDKs, and CLI in one Rust binary.
Sieveon Memory MCP
A workload-adaptive agent memory system combining event logs, knowledge graphs, and vector embeddings
Mini Chatchat
Full-stack AI knowledge workspace with hybrid RAG, web search, tool-using agents, MCP integration, authentication, user isolation, and Docker deployment.
Kontor
Real-time monitoring and control dashboard for locally running Claude Code agents
Notebooklm Py Diet MCP
Streamlined MCP server for Google NotebookLM: 14 workflow-oriented tools for AI agents (the practical companion to notebooklm-py-MCP).
Farscry
Farscry: see through any image. Converts screenshots into structured context for AI agents. OCR + layout analysis + TOON output. Zero API cost. Single binary.
A2a Superhub
Durable A2A coordination with opt-in Markdown memory, offline inboxes, knowledge graph and timeline, plus authorized Qdrant hybrid retrieval.
Clavion
Secure crypto runtime for autonomous agents — key isolation, policy enforcement, and multi-chain transaction management
Agenium Python
Python SDK for AGENIUM — AI agent identity, discovery & trust. MCP-compatible. pip install agenium
Fishi
FISHI — Vibe coding meets CLI. Describe what you want, agents build it. AI-Powered Software Delivery Pipeline with Governance.
Agent Action Shield
Human-in-the-loop approval UI for AI agent tool calls. Risk-tiered confirmation, drop-in React and Vue components, and a tamper-evident audit trail of every decision. Zero runtime…
Map Standard
Estándar declarativo que acota el contexto, limita las herramientas y capa el coste de un modelo por tarea. Disciplina enforzada por código, no agentes.
AINativeOS
The open OS for building an AI-native company in hard-mode sectors. A 15-chapter Handbook, a 90-term Dictionary, and 24 runnable skills for Claude Code, Codex, Cursor, and Gemini.…
Cognitive Coalition
Claude Code-first reasoning skill: budgeted role debate, private ledger, scenario playbooks, and prompt CLI for sharper plans with less token waste.
Enterprise AI Knowledge Ops
Enterprise AI knowledge operations platform using Azure OpenAI, Azure AI Search, RAG, agentic workflows, tool-calling agents, Durable Functions, and enterprise observability patte…