mcpField
Q
qingkuai-mcp-server

qingkuai-mcp-server

Local
github.com/qingkuai-jsDeveloper Tools3Updated 1d ago
Repository

About qingkuai-mcp-server

qingkuai-mcp-server is the MCP component of the QingKuai language tooling workspace, for AI assistants working with `.qk` files. It provides QingKuai tools and analysis as part of a toolchain that also includes language services, an LSP server, and a VS Code extension.

Key features

  1. 01QingKuai language analysis
  2. 02MCP tools for AI assistants
  3. 03Language service and diagnostics
  4. 04LSP server
  5. 05VS Code extension and syntax highlighting

Use cases

  1. 01Assist AI work on `.qk` files
  2. 02Analyze QingKuai code
  3. 03Use QingKuai language tooling in VS Code

MCP support

The MCP server provides QingKuai tools and analysis to compatible AI assistants.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "qingkuai-js-qingkuai": {
      "command": "npx",
      "args": [
        "-y",
        "qingkuai-mcp-server"
      ]
    }
  }
}
Run commandnpx -y qingkuai-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmqingkuai-mcp-server1.0.2

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
filePathstringYesAbsolute or workspace-relative path to the .qk file to format and write back

Details

From the project README

Qingkuai Language Features

Qingkuai Language Features is the official language tooling workspace for QingKuai files (.qk).

It contains the full toolchain used by the VS Code extension, including:

  • language grammar and syntax highlighting
  • language service (analysis, completion, formatting, diagnostics)
  • language server (LSP)
  • TypeScript plugin integration

Workspace Packages

PackageDescription
packages/language-serviceCore language intelligence and compiler-adapter logic
packages/language-serverLSP server on top of language-service
packages/vscode-extensionVS Code extension client + grammar + commands
packages/typescript-pluginTS server plugin for QingKuai-specific behavior
packages/mcp-serverModel Context Protocol server for AI assistant integration

Install Vscode Extension

Install from VS Code Marketplace:

After installation, open any .qk file to activate the extension.

Features
  • Rich Syntax Highlighting — Full support for .qk files and embedded languages (js/ts/css/sass/scss/less/stylus/postcss)
  • Smart Completions — Context-aware suggestions for directives, attributes, slots, and events
  • Hover Documentation — Instant inline help with type information for directives and framework keywords
  • Type Checking & Diagnostics — Real-time analysis powered by compiler integration, including generic type validation
  • Code Navigation — Go to Definition / References / Rename / Code Lens / Signature Help support
  • Document Formatting — Prettier-based formatting with Qingkuai-specific rules and support for component tags with generic parameters
  • AI Integration — Optional Model Context Protocol (MCP) server support for AI assistant tools

Local Development

Requirements
  • Node.js 18+
  • pnpm 8+
Setup
git clone https://github.com/qingkuai-js/language-features.git
cd language-features
pnpm install
Build
npm run build

This command builds all packages via Rollup and emits outputs into dist directories.

Watch Mode
npm run dev
Grammar Build (extension package)
cd packages/vscode-extension
npm run build:grammars
Packed Payload Check (extension package)

Before publishing, run this after npm run build:

cd packages/vscode-extension
npm run verify:packed

It stages the files VS Code would ship (per .vscodeignore and the production dependencies), then boots the language server and the MCP server from that layout with the host typescript injected and no typescript package on disk. Pass --keep to keep the staged directory for inspection. Stop watch mode (npm run dev) first: it rewrites dist with a development build that keeps dependencies external, which the check will (correctly) reject.

Architecture Overview

  1. VS Code extension starts and launches the QingKuai language server.
  2. Extension configures the TypeScript plugin (typescript-plugin-qingkuai) for tsserver.
  3. Language server delegates core analysis/format/diagnostics to qingkuai-language-service.
  4. Language service integrates compiler output and framework-specific semantics.
  5. Optional: MCP server provides QingKuai tools and analysis to compatible AI assistants (Claude, etc.)

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.