Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Shared MCP client foundation for connecting agent frameworks to KeeperHub.
This repo holds the small, framework-agnostic MCP kernel that framework adapters (Eliza, OpenClaw, Hermes, and others) build on. It is not itself a framework plugin — the per-framework plugins live in their respective framework ecosystems and import these clients.
| Package | Language | Path | Registry |
|---|---|---|---|
@keeperhub/mcp | TypeScript | packages/mcp | npm |
keeperhub-mcp | Python | python | PyPI |
Both clients implement the same kernel:
401/404kh_ vs wfb_ key disambiguationv0.1.0 — MCP HTTP transport implemented (session bootstrap, tools/call, 401/404 re-init, API key helpers). Ready for first publish to npm and PyPI. See .github/workflows for release tags (npm-v*, py-v*).
Per the KeeperHub SDK strategy, framework plugins ship from their own ecosystems, not this repo:
@elizaos/plugin-keeperhub (ElizaOS org)For agent users: point your MCP client at https://app.keeperhub.com/mcp directly when your framework supports MCP natively.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.