Drag-and-drop MCP server scoping for Claude Code.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"eidos-mcp-registry","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Eidos MCP Registry **MCP server management for professional developers who work across dozens or hundreds of repos.** You have 20+ MCP servers installed. You work across 100+ repos. Every server in `~/.claude.json` leaks into every project — your staging credentials visible in client repos, your internal tools cluttering projects that don't need them, Claude burning thousands of tokens evaluating tools it will never use and picking the wrong one because it's choosing from 200+ options instead of 20. Editing `.mcp.json` by hand in every repo doesn't scale. The Eidos MCP Registry gives you a single local UI to organize MCP servers into groups, deploy scoped configs across all your repos at once, and enforce that servers only appear where they belong. Built for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). Open source. Free.  ## What It Does - **Group-based scoping** — organize servers by client, team, or project. Client A's repos only see Client A's tools. - **One-click deploy** — write `.mcp.json` to every repo in a group. Merge-safe: your hand-edits are preserved. - **Secrets masking** — API keys are automatically replaced with `${VAR}` references. Secrets never touch disk. - **Scope Audit** — instantly see which servers are leaking to unintended projects. One-click Promote to fix. - **Token budget visualization** — see exactly how many tokens you're burning on tool schemas and how much scoping saves. - **Detection scans** — automated drift, health, new-repo, gitignore, and tracked-despite-gitignore checks. - **Snapshot + rollback** — every deploy creates a restore point. One click to undo. - **Notification inbox** — prioritized alerts with approve/dismiss and audit proof. - **Server catalog** — completeness scoring (A–F), auto-enrichment from filesystem. - **280+ tests** — unit, API…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.