Launching today
MCPVault
5,000+ MCP servers with quality grades and live testing.
2 followers
5,000+ MCP servers with quality grades and live testing.
2 followers
MCPVault is the independent quality directory for MCP servers. Browse 5,000+ servers with quality grades (A to F), staleness signals, install commands, and client compatibility. Verification is real: we spawn the server and run an actual MCP handshake (initialize + tools/list). Verified servers earn a do-follow link and an embeddable README badge. Maintainers claim their listing with GitHub sign-in in under a minute. Claiming and verification are free during early access.
Hey Product Hunt
If you have tried wiring Claude, Cursor, or ChatGPT to real tools via MCP, you know the pain: tens of thousands of public MCP servers, and no way to tell which ones are maintained, which ones actually start, or which clients they support.
So I built MCPVault, the independent quality directory for MCP servers.
What it does:
5,000+ MCP servers, auto-ingested from GitHub and npm, refreshed nightly.
Quality grades (A to F), staleness signals, install commands, client compatibility flags.
26,000+ tool-level pages: every tool inside a server gets its own page.
Real verification: we spawn the server and require an actual MCP handshake (initialize + tools/list). Re-checked weekly. If it stops working, the badge lapses.
Maintainers claim their server with GitHub sign-in, fix the listing, and request verification. Free during early access.
Verified servers earn a do-follow website link and a status-aware embeddable badge.
There is even an official MCP server: npx -y mcpvault-mcp lets you search the vault from inside Claude or Cursor. It is verified server #2 in its own directory, naturally.
Why it is different:
The "Verified & Working" badge is earned, never bought. Verification means the server actually ran and answered a real MCP handshake, not that someone paid for a checkmark. Smithery was recently acquired; the ecosystem needs an independent quality layer, so I built one.
Free for everyone. Happy to talk about the verification harness, the grading heuristics, or the MCP ecosystem in general.
Henrik
We launched MCPVault, an independent directory for MCP servers, on Fazier yesterday and it won Product of the Day.
The best part was not the badge. The launch comments gave us a very clear product roadmap, so we treated them like issues and shipped fixes during the launch window.
What we added today:
Last verified date on every verified listing, based on the last successful live test.
Live test evidence: MCP protocol revision, server version, tool count, and verifier runtime.
Weekly re-verification: a verified server must still complete initialize plus tools/list. If it fails, the badge lapses automatically.
Maintainer activity filters: browse servers updated in the last 30, 90, or 365 days.
Auth method filters: owners can declare whether a server needs no auth, an API key, OAuth, or another method.
Clearer grade disclosure: unclaimed listings now explicitly say their grade is automated from public GitHub signals, not maintainer-reviewed.
Trust cadence copy: grades and repository signals refresh nightly, live tests run weekly.
A production bug fix: our nightly GitHub refresh was overwriting owner-edited listing details. Fixed before it could cause damage.
The broader idea behind MCPVault is that a directory should distinguish between “this repository exists” and “this server actually responded to a real MCP call recently.”
Still early, but this was a good reminder: launch feedback is most valuable when you can convert it into shipped product improvements quickly.