Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Qlane MCP plan tests for my current local diff"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Installs Qlane MCP into your AI coding editor, so your agent can reach your Qlane projects, test targets and what Qlane found on your pull requests without leaving the editor.
To install and use it, see the plugin's README.
Path | What it is |
| The plugin: everything that ships to an editor, and the folder Anthropic's directory reviews. |
| The marketplace Claude Code, Codex and VS Code install from. It points at |
| Cursor's marketplace, pointing at the same folder. |
| The server's entry in the official MCP Registry, as |
| Maintainer claim for the server's listing on Glama. |
| Development tooling: formatting, linting, schema validation, tests. None of it ships. |
Related MCP server: TestCollab MCP Server
The development tooling lives in tooling/, its own npm package, outside the plugin folder, so
none of it ships. A test pins the plugin folder to the files that do.
npm ci --prefix tooling
npm run check --prefix toolingcheck runs Prettier, markdownlint, JSON Schema validation of the portable manifests, and the
unit tests, over the whole repository. It makes no network calls, so it works offline and in a
sandboxed CI runner.
npm run format --prefix tooling # apply Prettier
npm run lint:md:fix --prefix tooling # apply markdownlint's safe fixesTwo checks need the Claude Code CLI and so are not part of check, which has to run on a
runner that does not have it:
claude plugin validate --strict . # the marketplace; --strict makes warnings fatal
claude plugin validate --strict plugins/qlane # the plugin itself
claude plugin tag --dry-run plugins/qlane # what the next release tag would beThe version lives in the plugin's manifests only. The marketplace entry deliberately declares no
version of its own: plugin.json wins at install time, so a second copy could only ever
agree or be silently ignored.
No manifest may contain a placeholder. Both regional URLs are literal strings in every
manifest. ${user_config.*} resolves only in the Claude Code CLI — the portable Agent Plugins
schema cannot even express userConfig (additionalProperties: false), and claude.ai treats
an MCP url as an opaque connector identity, so a templated host reaches registration verbatim
and fails to resolve. A test enforces this.
MIT.
This server cannot be deployed
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
Change-aware CI validation and affected-test guidance for coding agents.
Approved test intent, reviewed Playwright automation and run evidence, inside your editor.
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
