- Agent Harnesses @ryanalberts/agent-harnessesAgent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1,125 GitHub stars.
- Tetrees MCP @tetrees/mcpOwn, grow and trade portable agent intelligence via TAIP/1 Packs and MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.304 GitHub stars.
- HeyClaude — Claude & AI workflow directory @jsonbored/heyclaudeSearch the HeyClaude directory of Claude Code agents, MCP servers, skills, and tools.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.300 GitHub stars.
- Qaskills @pramoddutta/qaskillsSearch, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.230 GitHub stars.
- Suede Skills MCP @jasoncolapietro/suede-skills-mcpRead-only access to 71 Suede skills: discovery, install options, SEO audits, A-F grading.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.127 GitHub stars.
- runx @runx/runxThe governed runtime for agent skills. Search the catalog and inspect a skill before running it.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.95 GitHub stars.
- Hexis @bevel-software/hexisGit-backed platform for skills, tools, and context for AI agents5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.94 GitHub stars.
- AAI Gateway @gybob/aai-gatewayUnified MCP & Skill management gateway, shared across AI agents, 99% context token savings7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.91 GitHub stars.
- NotebookLM Secure @pantheon-security/notebooklm-mcp-secureSecurity-hardened NotebookLM MCP with post-quantum encryption10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.85 GitHub stars.
- Pulse Subregistry @pulsemcp/pulse-subregistryMCP server providing access to the PulseMCP Sub-Registry for browsing and discovering MCP servers.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.81 GitHub stars.
- Skillsmith @smith-horn/skillsmithShare agent skills across your team, scan them for risk, and track what's actually used.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.76 GitHub stars.
- DNS Aid @dns-aid/dns-aidDiscover and publish AI agents via DNS using SVCB records (RFC 9460)6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.70 GitHub stars.
- Skill of Skills @911fund/directoryQuality-ranked, cross-platform directory of AI coding skills, plugins and MCP servers.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.64 GitHub stars.
- Neuronto ARD Registry: Agentic Resource Discovery (ARD) Index @neuronto/agents-tools-search-discovery-ard-registryNeuronto ARD Registry: one search across every public ARD registry + 200,000+ verified MCP tools4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.60 GitHub stars.
- Agoragentic Agent OS MCP @rhein1/agoragenticTriptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.40 GitHub stars.
- DeFi Trading Agents @nirholas/defi-agentsDeFi agent definitions JSON API - crypto trading portfolio management bots7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.35 GitHub stars.
- Bhived MCP @artkeyai/bhived-mcpShared knowledge graph, skills, and tool discovery for AI agents through the Model Context Protocol.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.35 GitHub stars.
- AI Tool Discovery Agent @nirholas/tool-discovery-mcpAI agent discovers MCP servers from GitHub npm - analyzes APIs configs6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.31 GitHub stars.
- Awesome Agent Skills @shadowrootdev/awesome-agent-skillsMCP server with 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.26 GitHub stars.
- A2ASearch @tadas-github/a2asearch-mcpSearch 10,000+ AI agents, MCP servers, and CLI tools via A2ASearch from any MCP client.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- Forage @isaac-levine/forageSelf-improving tool discovery for AI agents. Find, install, and use new MCP servers automatically.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
Agent & MCP directories MCP servers
A server here a directory, registry or marketplace for finding, hiring or listing AI agents, MCP servers or agent skills.
Not here: job boards for people and app stores.
1,886 remote374 localTagged by Odel's AI, which can make mistakes
Most popular in Agent & MCP directories
By GitHub stars, at most two per publisher- Number 1: Agent Skills Search Server@mcp/skills-searchSearch and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.26,028 GitHub stars.
- Number 2: MCP Registry Server@mcp/registryPublish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.7,314 GitHub stars.
- Number 3: Pm Claude Skills@mohitagw15856/pm-claude-skills1285 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1,425 GitHub stars.
