- 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.
Samia
SAM/IA — biologically-inspired persistent memory for AI agents: tiered decay, dual-process recall (episodic chainograms + semantic atoms), restorable supersession, REM-cycle conso…
Skill Awesome
Skill that will help you during vibe coding
Oncall Copilot
Provider-agnostic AI on-call assistant — RAG + a tool-using agent + an MCP server + an eval harness — runs on Claude, OpenAI or OpenRouter. A hands-on learning project.
Glia
AI agent skill synthesizer ΓÇö local-first, air-gappable, graph+vector+causal retrieval over a community catalog. Rust CLI + Hub, SurrealDB, OpenBao, candle embeddings.
Aeryn
Cross-application AI agent control plane. The invisible layer that coordinates Claude Code, Codex, Gemini, and Cursor as one team.
Delega CLI
Maintenance-mode CLI for the privately operated Delega deployment; public engineering artifact.
Cachly Go
Official Go SDK for cachly — persistent AI memory and managed Valkey/Redis with semantic caching. Free tier, EU-hosted.
Cachly Java
Official Java SDK for cachly — persistent AI memory and managed Valkey/Redis with semantic caching. Free tier, EU-hosted.
Metaclaw
Node.js orchestrator for Claude agents running in isolated containers, controlled through messaging channels.
Restless
Turn any OpenAPI-powered REST API into an MCP server in one command.
Leanzero MCP Doc Processor
This is a Model Context Protocol server that helps you work with PDF, DOCX, and Excel files in a more intelligent way. The server extracts text, understands document structure, pu…
Awesome Native Agent Platforms
Curated list of runtimes, sandboxes, browsers, model routers, protocols, and infrastructure for production AI agents.
Lab.abvx
Public catalog and control plane for the ABVX AI coding tools stack: repo context, orchestration, skills, discovery, and proof surfaces.
Aikit Runtime
Agent-native, governed AI runtime for Rust, Python, and TypeScript — native providers, MCP, tools, routing, memory, budgets, audit, and containment.
Cinema Ops Platform
A local, fully-proven data platform for cinema exhibition data — four unlike sources, an append-only bronze layer, a governed gold layer, and an AI agent tool set with no personal…
The Conductor Hermes
Skillset module + MCP for AI agent harnesses. Enhances Hermes (plugin) and external meisters (stdio MCP). Pillars, Remnants, safety spine. Plugin XOR MCP.
Incident Reporting Navigator Skill
Agent skill: one security incident mapped across EU reporting regimes (NIS2, GDPR, DORA, CRA) — duties, authorities, deadlines, cited live via the Ansvar Gateway MCP connector
Pi Mem
Harness-verified memory recall for coding agents — re-checks a memory note against ground truth on read (verified/stale/unverifiable). Built on the pi-gate trust boundary.
Swarmbreaker
Load and chaos testing for AI agent orchestration plumbing: adversarial mock model endpoint + mock MCP tool fabric, knee detection with CIs, honest confidence labels.
Agentic CAD Skills
The tool layer for CAD agents: skill definitions, MCP interfaces, typed tools and post-condition checks. Part of the Agentic Mechanical Engineering collection by WOGO.
Layerdraw
A typed, layered graph platform for defining structure once and deriving reproducible views.
Capability Radar
A Codex skill for discovering, evaluating, and recommending open-source AI and software capabilities.
Novahiz
Agent governance toolkit for AI coding agents. Classifies prompts, requires the right skills before file edits, and blocks unsafe changes. Runs fully local with no model calls. Sh…
Agy Agent Acp
Agent Client Protocol (ACP) adapter for Google Antigravity CLI (agy)
Agent Workspaces
Плагин для работы Codex и Claude в Trelio
Threatveil Oss
Open-source assurance infrastructure for tracking whether security evidence still applies as autonomous AI systems change.
Compliance Drift Sentinel
AI agent that predicts downstream report breakage from upstream schema changes using DataHub lineage — Build with DataHub Agent Hackathon (Wildcard)
Wat Framework Starter
WAT (Workflows, Agents, Tools): starter kit para operar tu negocio con Claude Code. La IA razona, el codigo ejecuta; memoria persistente en un vault.
People Memory MCP
A private people graph that gives your AI agent durable memory
Burndrop
One-time, end-to-end encrypted secret exchange between humans and AI agents through a zero-knowledge relay
Enggraph
Engineering Graph for AI coding agents. Code intelligence, persistent memory, plans and multi-project context over MCP.
Neuromedia Repowise
Russian derivative distribution of Repowise for local code intelligence and MCP integrations
JevCompass
Tool and skill suggestions for Codex Desktop and CLI, with local-first privacy and optional Jev ranking
Scopelens
Your agent needs to read code. Why can it write? Evidence-aware GitHub permission reviews and static MCP configuration checks.
M8m
AI memory observability, provenance & security
Deadalus
AI-powered architecture studio: prompt → plan → BIM. Electron app + MCP servers for Revit + local QLoRA training on consumer GPUs.
Jazari Codex
Curated catalogue of tiered agent skills and verified MCP connectors for Jazari
Awesome Ag Ui
AG-UI protocol: 340+ agent integrations, SDKs, middleware, and apps, with a capability matrix per framework.
YourHand Community
YourHand Community — open-source, permission-aware Windows device control via MCP (source preview).
Mandatepay
Authorization firewall for agentic payments: signed mandates, policy-as-code, human approval and verifiable audit.
Skills Brain
Local-first visual capability graph & MCP manager for Agent Skills / Codex. 将散落的 Agent 技能串联成可交互的能力网络。
Dsh Web Bridge MCP
Delegate coding to DeepSeek Harness through MCP while keeping conversations in its Web UI
Deterministic Agent Gatekeeper
Determinism you can prove for AI agent tool calls: a pure decision core whose every verdict re-derives hash-exact from its record.
Pile
Pile — open-source, agent-native issue tracker on Cloudflare Workers. Linear alternative with MCP, CLI, and built-in agent dispatch (Devin, Cursor, Codex).
Rewind Bench
A benchmark separating repairs that passed from repairs that held up. Bugs are injected by AST mutation; every accepted repair is re-run against a hidden second dataset
Restoregap
Prove your recovery works — then refuse the risky change until it does. Zero-config drift check, sandboxed restore drills, and a preflight gate for you and your coding agents. One…
Context Bank
Context infrastructure for LLMs — portable memory, model switching, skills & governance. Switch GPT ↔ Claude ↔ Gemini; your context stays. npm: @losi-ai/*
Libre Box
Self-hosted LibreChat + MCP stack that gives AI agents a real, persistent Linux computer — shell, TTY sessions, background jobs and files in a hardened Ubuntu sandbox.
Hisho Kun
Remote Approval Companion & Desktop Pet for AI Coding Agents (Claude Code, Cline, Cursor)
Agent Engineering Roadmap
从会调 LLM API 到能把 Agent 送上线：按依赖关系排的六阶段学习路线（中英双语）· An opinionated roadmap for becoming an AI agent engineer