Remote OpenClaw is the largest open directory of building blocks for AI coding agents: 13,000+ MCP servers, agent skills, plugins, and ready-made workflows for Claude Code, Codex, OpenClaw, and Hermes. Stop hunting across GitHub, npm, and scattered docs. Find, compare, and install everything in one place. Filter by client, category, and use case, copy the install command, and go. Free to browse, no login required.
Hey Product Hunt 👋
I kept losing time hunting for the right MCP servers, skills, and plugins for my AI agents, scattered across GitHub repos, npm, Discord threads, and half-updated docs. There was no single place to find and compare them.
So I built Remote OpenClaw: an open directory of 13,000+ MCP servers, agent skills, plugins, and workflows for Claude Code, Codex, OpenClaw, and Hermes. Search by client or use case, grab the install command, and you're going in seconds. Free to browse, no login.
Would love your feedback. And if there's a server or skill you think belongs in here, drop it below and I'll add it 🙏
The copy-the-install-command flow across 13k+ servers is the part I would actually use — hunting MCP servers across GitHub, npm, and Discord is exactly the pain. Since these are third-party servers that run with real permissions inside a coding agent, do you surface any trust signal (source repo, maintainer, last updated) next to the install command, or is vetting left to the user? Also curious whether you dedupe near-identical servers or just list them all.
Installing cleanly is table stakes, but the thing that actually made me drop servers was the cost of just having them connected. One I tried registered 41 tools and ate roughly 12k tokens of context before the agent did anything, and with three servers attached it started picking the wrong tool because the list got too long to reason over. Does the directory expose tool count and total schema size per server? That is the number I would sort by.
love how the install command copy-paste flow just works — that little detail of skipping the docs scavenger hunt is exactly what i needed
Love that the install commands are right there alongside the filters, no extra clicks needed. The directory feels fast and clean too, not like the usual bloated registry pages.
Love having everything in one spot, the copy-paste install command alone saves me a ton of clicks. One thing that would be huge: a "last verified working" date or health badge per listing, since MCP servers go stale fast and I'd rather know before wiring one into a project.
The filter by client, category, and use case setup is genuinely thoughtful, makes sorting through 13k+ entries feel manageable instead of overwhelming. Nice execution on something most directories botch.
Love that this exists, the copy-paste install flow is exactly what I needed today. One thing that would make it even better: a community upvote or "works on" badge so I can quickly tell which MCP servers are actually maintained and battle tested versus abandoned. Right now everything looks equal at a glance.
Honestly love that you can just copy the install command straight from the listing, no extra clicks or digging through docs. Filtering by client and use case upfront is the kind of thing that sounds small but saves a ton of time when you're setting up a new agent.
Would love to see a "compatibility check" feature that warns you if an MCP server or skill hasn't been updated for your specific client version before you copy the install command, saves people from troubleshooting broken installs later.
This is useful for anyone building with coding agents seriously. The hard part is not just finding one MCP server, it is knowing which client it works with, how to install it, and whether there is a better option for the same use case.
Curious how you’re handling quality signals as the directory grows. Are servers ranked mostly by metadata like GitHub activity and package info, or do you plan to add usage/reliability signals too?
About Remote OpenClaw on Product Hunt
“13,000+ MCP servers, skills & plugins for AI coding agents”
Remote OpenClaw launched on Product Hunt on July 22nd, 2026 and earned 94 upvotes and 23 comments, placing #21 on the daily leaderboard. Remote OpenClaw is the largest open directory of building blocks for AI coding agents: 13,000+ MCP servers, agent skills, plugins, and ready-made workflows for Claude Code, Codex, OpenClaw, and Hermes. Stop hunting across GitHub, npm, and scattered docs. Find, compare, and install everything in one place. Filter by client, category, and use case, copy the install command, and go. Free to browse, no login required.
Remote OpenClaw was featured in Developer Tools (516.2k followers) and Artificial Intelligence (474.3k followers) on Product Hunt. Together, these topics include over 185.6k products, making this a competitive space to launch in.
Who hunted Remote OpenClaw?
Remote OpenClaw was hunted by Aaron. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Remote OpenClaw stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Aaron