Testers.ai CARBON Test Harness Lite MCP server

CARBON Lite — local skills and optional background checks

The eight CARBON Lite workflows plus a portable Studio workspace. Open source under MIT, readable JavaScript. The Codex plugin needs no MCP server, OAuth, account, analytics, hosted service or CARBON model calls. Built by testers.ai. This is a separate edition; it does not replace the existing Claude package or the original Studio submission. The separate private CARBON Studio Pro edition preserves the full local MCP experience. Lite is the first package intended for submission.

Standalone MCP distribution

For MCP clients and directories, use the separate local MCP bundle. It adds stdio tools and prompts around the Lite evidence engine, not Pro features. The Codex plugin ZIP remains serverless.

Install in Codex

Download the ZIP from Releases, extract it, and use your Codex version's local-plugin installation flow to select that folder. This repository is not a claim of public directory approval. After installation, start a fresh conversation and run /carbon (select CARBON Lite's carbon command in the host's skill picker if it requires a plugin prefix). CARBON tests the current project when the target is clear. Otherwise it asks what to test: provide a URL, folder, repository, API, app, feature, or requirements. It runs a broad assessment within the configured budget and reports findings, evidence-qualified confidence, coverage gaps, and prioritized next steps. Host capabilities and permissions determine which tests can actually run.

License

CARBON Lite is open source under the MIT license. You may use it at work, fork it, modify it, redistribute it, and sell copies, preserving the required copyright and license notices. Third-party dependency licenses remain intact; see NOTICE.md. There is no trademark endorsement grant.

Commands

Invocation prefixes depend on the host. A useful first request is: “Use CARBON Lite to assess this project and show the evidence report.”

Skills can analyze supplied requirements or results without a local runtime. Hands-on testing needs the host's browser/terminal/API capabilities. The optional evidence helper requires Node 22+, already bundled as readable JavaScript: no npm install for archive users. Demo artifacts may require Python or their documented test framework; creating a copy neither installs dependencies nor starts a server.

What is and is not equivalent

Included: the Light investigation methods, four disposable demos/two test profiles, local preferences, revisioned evidence/history, findings, persona journeys, screenshots, scope-qualified confidence, portable HTML/JSON, screenshot enlargement, map/check inspection and explicit feedback import/export.

Different from MCP Studio: no native global/settings entrypoint, MCP tools, automatic host message handoff, unattended UI write-back, or guaranteed in-chat live rendering. The report is a normal HTML artifact. Supporting browsers can watch a user-selected snapshot file; others need reload/import. UI feedback is a draft until imported. Not included: Pro commands, proprietary benchmarks, hosted sharing, cloud execution, continuous loops or cross-build/3D map features. This is not full native-UI parity.

Cost and privacy

Shortened. The full README is on GitHub.