Compare two AI tools side by side
Put any two skills or MCP servers next to each other: risk grade, what each can access, how popular it is, and how to install it.
| What | metaharness | @metaharness/kernel |
|---|---|---|
| Risk grade | DD · High risk signals Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee. | CC · Moderate risk signals Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee. |
| Type | App connector | App connector |
| Est. context load | ~550 tokens / turn (~3 tool schemas, 0.27% of 200k context) | ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context) |
| GitHub stars | — | — |
| Weekly npm downloads | 61.8k | 30k |
| Local files | No local folder access noted | No local folder access noted |
| Command execution | No shell command runner noted | No shell command runner noted |
| Network reach | Fetches arbitrary web URLs | Fetches arbitrary web URLs |
| Credentials | Requires API key or token | No API token required |
| Package source | npm (metaharness) | npm (@metaharness/kernel) |
| Install command | npx -y metaharness | npx -y @metaharness/kernel |
| Bottom line | Use this tool only with repos you trust completely, run it in an isolated environment, and carefully review the generated agent code before deploying it to production systems. | Use MetaHarness only on non-sensitive projects, verify generated code before running it, and never use it with repositories containing secrets or private data. |
Based on public adoption and transparency signals as of Oct 29, 2026. Our opinion, not a code audit or security guarantee.
Go deeper
Want to inspect exact published files, install hooks and network hosts?
Run a pre-install check on any package, MCP config or SKILL.md, or open a full report with PDF export.