Qlane MCP
Integrates Qlane test management into AI coding editors, enabling agents to view projects, test targets, and test case counts, and plan tests for local diffs.
README
Qlane agent plugin
Installs Qlane MCP into your AI coding editor, so your agent can reach your Qlane projects, test targets and test-case counts without leaving the editor.
Which region?
Qlane runs two independent regional stacks. The plugin registers one server for each, and you connect the one hosting your organization:
| Server | Endpoint |
|---|---|
qlane-eu |
https://mcp-eu.qlane.ai/api/mcp |
qlane-us |
https://mcp-us.qlane.ai/api/mcp |
Authenticate that one and leave the other alone. An unconnected server contributes none of its own tools — your editor shows it with two sign-in helpers and nothing else — so it costs you nothing and is not an error state. If you connect the wrong one, every call returns a 403 naming the correct host — nothing is lost, and the fix is to connect the other server.
Both are plain static URLs, so this works identically on every editor. Nothing is configured, substituted, or typed.
Install
Qlane MCP requires a Qlane account. Your editor prompts you to sign in the first time it calls the server.
Claude Code
claude plugin marketplace add qlaneai/agent-plugin
claude plugin install qlane@qlane-plugin
Then run /mcp and authenticate qlane-eu or qlane-us — whichever hosts your
organization. There is no configuration step and nothing to type.
VS Code and GitHub Copilot
Add this repo to chat.plugins.marketplaces:
{
"chat.plugins.marketplaces": ["qlaneai/agent-plugin"]
}
If nothing appears after adding it, check that chat.plugins.enabled is true.
Cursor
Cursor reads the root plugin.json and loads this plugin without changes. Add the repository
as a marketplace, install qlane, then authenticate the server for your region.
Kiro
Same as Cursor — add the repository, install, authenticate your region's server.
Codex
Codex splits this across two places: you register the marketplace on the CLI, but you install from it in the ChatGPT desktop app. There is no CLI install command.
codex plugin marketplace add qlaneai/agent-plugin
Then open the Plugins Directory in the ChatGPT desktop app and install qlane from it.
Codex prompts you to sign in the first time it calls the server.
Opening this repository in Claude Code
You will see qlane-eu and qlane-us listed as Pending approval. That is expected and
harmless: Claude Code reads a .mcp.json at a repository root as project-scoped MCP
configuration, so this repo's .mcp.json — the plugin's own manifest — is being read as if it
were yours. Decline it, and install the plugin with the commands above instead.
Without the plugin
Any MCP client can point at the endpoint directly. For Claude Code:
claude mcp add --transport http --scope user qlane https://mcp-eu.qlane.ai/api/mcp
Swap the host for mcp-us.qlane.ai if your organization is US-hosted.
What it can do
Read your projects, test targets and test-case counts, and plan tests for a local diff before a pull request exists. Planning a test consumes Qlane credits.
Development
npm ci
npm run check
check runs Prettier, markdownlint, JSON Schema validation of the portable manifests, and the
unit tests. It makes no network calls, so it works offline and in a sandboxed CI runner.
npm run format # apply Prettier
npm run lint:md:fix # apply markdownlint's safe fixes
Two 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 . # manifest shapes; --strict makes warnings fatal
claude plugin tag --dry-run # what the next release tag would be
The version lives in plugin.json 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.
License
MIT.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.