dotvvm-docs-mcp
Enables AI assistants to access DotVVM UI control documentation, including listing controls and retrieving detailed docs with code samples.
README
dotvvm-docs-mcp
An MCP (Model Context Protocol) server that exposes DotVVM UI control documentation to AI assistants. Documentation is sourced directly from the riganti/dotvvm-docs GitHub repository (branch 4.0) and cached locally for 30 days.
Status: Early prototype — not yet stable. Expect breaking changes. Not yet published to npm. The
npx @madev/dotvvm-docs-mcpinstall instructions below will work once the package is released.
Prerequisites
- Node.js 18+ (native
fetchrequired) - npm
Development setup
npm install
npm run dev # runs via tsx (no build step needed)
npm run dev starts the server on stdio. It does not print a prompt — this is expected, since MCP servers communicate over JSON-RPC on stdin/stdout.
Building
npm run build # compiles TypeScript to dist/
npm start # runs compiled output
MCP tools
| Tool | Description |
|---|---|
list_dotvvm_controls |
Lists all discovered controls. Accepts optional category or prefix filter. |
get_dotvvm_control_docs |
Returns composed Markdown docs for a control (description, HTML output, code samples, ViewModels). |
Control naming
DotVVM controls are identified by a tag prefix that maps to a namespace:
| Prefix | Namespace / Category |
|---|---|
dot: |
Built-in controls (builtin) |
auto: |
Auto UI controls (builtin-autoui) |
bs: |
Bootstrap 3 (bootstrap) |
bs4: |
Bootstrap 4 (bootstrap4) |
bs5: |
Bootstrap 5 (bootstrap5) |
bp: |
Business Pack + Messaging (businesspack, businesspack-messaging) |
Use prefix:Name syntax to disambiguate controls that exist in multiple namespaces — e.g. dot:Button, bp:GridView, bs5:Alert.
Integrating with Claude Code
Add to your Claude Code MCP config (.claude/settings.json or global settings):
{
"mcpServers": {
"dotvvm-docs": {
"command": "npx",
"args": ["-y", "@madev/dotvvm-docs-mcp"]
}
}
}
Integrating with Claude Desktop
Add to %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"dotvvm-docs": {
"command": "npx",
"args": ["-y", "@madev/dotvvm-docs-mcp"]
}
}
}
Restart Claude Desktop after editing the config.
Local development
To use a local checkout instead of the published package:
{
"mcpServers": {
"dotvvm-docs": {
"command": "npx",
"args": ["tsx", "/path/to/dotvvm-docs-mcp/src/index.ts"]
}
}
}
Caching
Control discovery and documentation are cached to disk at:
~/.dotvvm-docs-mcp/cache/
├── _registry.json # control list (from GitHub API)
├── builtin__Button.json # per-control docs
└── ...
Cache TTL is 30 days. To force a refresh, delete the relevant .json file or the entire cache directory.
Project structure
src/
├── index.ts # MCP server entry point, tool definitions
├── controls.ts # Control discovery via GitHub API + prefix resolution
├── fetcher.ts # Raw content fetcher + Markdown composition
└── cache.ts # File-based disk cache (30-day TTL)
Data source
All documentation is fetched from:
- Directory listings:
https://api.github.com/repos/riganti/dotvvm-docs/contents/Controls/{category}?ref=4.0 - Raw content:
https://raw.githubusercontent.com/riganti/dotvvm-docs/4.0/Controls/{category}/{ControlName}/
Each control directory may contain control.md, output.md, and sample{N}/ subdirectories with page.dothtml, ViewModel.cs, and sample.md.
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.