The MCP 2026-07-28 spec moved the protocol to a stateless core, removed the HTTP+SSE transport, and aligned authorization with OAuth 2.1. Hundreds of public MCP servers now silently fail it, and directories list servers without auditing any of them. Scorecards grade public servers against a published, versioned rubric, from source, at a pinned commit, with evidence for every result.
We graded ourselves first, with the same rubric and no courtesy window: findings against our own server ship immediately. This is the registry's own catalog server, the one behind clauderegistry.com/mcp.
Single Streamable HTTP endpoint; stateless transport; no HTTP+SSE surface.
Fresh server per request, no session map and no per-IP state; module caches hold only shared public data.
Current MCP SDK handles the handshake; the one declared capability (tools) is fully implemented.
Authless over read-only public catalog data, which the rubric permits with proportionate abuse controls; every tool serves cached or static data, so there is no expensive surface to abuse.
Complete schemas with descriptions, honest annotations (all tools read-only, none open-world), structured errors, bounded outputs.
No subprocess execution, no filesystem writes, no repository cloning, no user file ingestion; zod validation on all arguments; no secrets in the repository.
If you build Claude Code plugins, the same idea already works today: connect the registry's MCP server and ask your Claude to run verify_plugin against your work-in-progress, before you publish. It hands Claude the recipe to run the exact seven checks that gate the Verified by ClaudeRegistry badge, locally, so your code never leaves your machine.
claude mcp add --transport http clauderegistry https://clauderegistry.com/mcpRun a public MCP server? Get graded, or re-graded at a newer commit. Open an issue with your repository and the commit to grade; drafts go to you before anything is published.
Request a scorecard