Independent, local-only watcher for the AI-skill supply chain: flags bait-and-switch changes in the pages skills and MCP tools reference. Sends nothing anywhere. Python CLI.
SkillWatch is an MCP server published by kuzivaai in the Security category: independent, local-only watcher for the AI-skill supply chain: flags bait-and-switch changes in the pages skills and MCP tools reference. Sends nothing anywhere. Python CLI.
Recent commit activity is the strongest signal that reported issues will get attention.
Install
From source
git clone https://github.com/kuzivaai/SkillWatch
This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
✦
Ask AI about SkillWatch
Powered by Claude · Grounded in docs
I know everything about SkillWatch. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v0.4.1v0.4.1 · 29 Jul 2026This release publishes corrections that existed only in the repository, and ships the first evidence in this project that is not self-authored. Corrections that reached no user until now 0.4.0 shipped on 2026-07-11 and its page carried two…
v0.4.0v0.4.0 · 29 Jul 2026SkillWatch periodically re-fetches the external URLs an AI agent skill or MCP tool config points at, hashes the content, and alerts when it changes — then runs best-effort regex triage over the diff. This release carries two dependency…
v0.3.0v0.3.0 — verifiable content ledger + external anchoring · 11 Jul 2026Highlights Verifiable content ledger** — append-only, hash-chained record of what each URL served, kept permanently even as snapshots prune. `skillwatch verify` / `skillwatch ledger [--export]`; streaming verify + export. External…
v0.2.0v0.2.0 · 8 Jul 2026SkillWatch v0.2.0 — periodic URL content monitoring for AI agent skills and MCP tools. What it does Watches the web pages that AI tools rely on and tells you when something changes. Runs 13 pattern checks on changed content to flag…
No package has been published for this server, so install it from source: clone the repository and follow its README.
Is SkillWatch safe to use with an AI agent?
Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.
Is SkillWatch still maintained?
Yes — the latest release is v0.4.1 (29 Jul 2026), and the last commit was 2 months ago. The repository has 0 stars.