Claude
Skills
Sign in
Back

dotnet-uno-mcp

Included with Lifetime
$97 forever

Using Uno MCP server. Tool detection, search-then-fetch workflow, init rules, fallback, citation.

AI Agents

What this skill does


# dotnet-uno-mcp

MCP (Model Context Protocol) server integration for Uno Platform live documentation lookups. Covers tool detection (`mcp__uno__` prefix), search-then-fetch workflow, initialization rules invocation, graceful fallback when MCP is unavailable, citation requirements, and safety guidelines for external data. Includes inline documentation that provides useful guidance without MCP server availability.

**Scope boundary:** This skill owns MCP server integration patterns for Uno Platform documentation. Core Uno development (Extensions, MVUX, Toolkit, themes) is owned by [skill:dotnet-uno-platform]. Per-target deployment is owned by [skill:dotnet-uno-targets].

**Out of scope:** General MCP protocol details. Uno Platform testing -- see [skill:dotnet-uno-testing]. Uno development patterns without MCP -- see [skill:dotnet-uno-platform] and [skill:dotnet-uno-targets].

Cross-references: [skill:dotnet-uno-platform] for core development patterns, [skill:dotnet-uno-targets] for deployment guidance, [skill:dotnet-uno-testing] for testing.

---

## MCP Tool Detection

The Uno Platform MCP server provides tools prefixed with `mcp__uno__`. Before using MCP tools, detect their availability.

### Available Tools

| Tool | Purpose |
|------|---------|
| `mcp__uno__uno_platform_docs_search` | Search Uno Platform documentation by query |
| `mcp__uno__uno_platform_docs_fetch` | Fetch full content of a specific documentation page |
| `mcp__uno__uno_platform_agent_rules_init` | Initialize agent session with Uno development rules |
| `mcp__uno__uno_platform_usage_rules_init` | Load common usage rules for Uno Platform development |

### Detection Logic

Check if Uno MCP tools are available by looking for tools with the `mcp__uno__` prefix. If the tools are listed in the available tool set, the MCP server is configured and reachable.

```
Detection steps:
1. Check if tools prefixed with mcp__uno__ are available
2. If available: use MCP workflow (search -> fetch -> cite)
3. If unavailable: fall back to static skill content and official docs URLs
```

**When MCP is available:** Use the search-then-fetch workflow for the latest documentation. MCP results are authoritative and current.

**When MCP is unavailable:** The static content in [skill:dotnet-uno-platform] and [skill:dotnet-uno-targets] provides comprehensive guidance. Reference official documentation URLs for the latest information.

---

## Initialization Rules

On first use of Uno MCP tools in a session, invoke both initialization tools to load authoritative development rules.

### Agent Rules Initialization

Call `mcp__uno__uno_platform_agent_rules_init` to load:
- Core identity and expertise scope for Uno Platform development
- IDE guidance (Visual Studio, VS Code, CLI) per operating system
- Knowledge routing rules mapping topics to canonical search queries
- Uno SDK features list (`UnoFeatures` supported values)
- Uno Extensions and Toolkit feature catalog

### Usage Rules Initialization

Call `mcp__uno__uno_platform_usage_rules_init` to load:
- Design system guidelines (Material preferred, responsive layouts)
- Data binding policy (MVUX vs MVVM binding patterns, forbidden WPF-isms)
- Navigation policy (prefer XAML attached properties over code-behind)
- Layout rules (AutoLayout, spacing scale, responsive breakpoints)
- Color and typography conventions (theme resources, no hardcoded values)
- Accessibility requirements (contrast ratios, touch targets, automation properties)
- Control-specific guidance (ItemsRepeater for lists, CommandExtensions, elevation patterns)

### Invocation Order

```
1. Call mcp__uno__uno_platform_agent_rules_init (loads routing rules and feature catalog)
2. Call mcp__uno__uno_platform_usage_rules_init (loads design and coding conventions)
3. Proceed with documentation searches using mcp__uno__uno_platform_docs_search
```

Both init tools are idempotent -- calling them multiple times in the same session is safe but unnecessary.

---

## Search-Then-Fetch Workflow

The primary workflow for retrieving Uno documentation uses a two-step pattern: broad search followed by targeted fetch.

### Step 1: Search

Use `mcp__uno__uno_platform_docs_search` to find relevant documentation pages.

```
Search parameters:
- query: descriptive search term (e.g., "MVUX reactive pattern", "Navigation Extensions")
- topK: number of results (default 8; use 15-20 for complex topics, 3-5 for specific queries)
- contentType: "prose" for guides, "code" for examples, null for all
```

Search results include:
- Document title and summary
- `SourcePath` (needed for fetch step)
- Relevance ranking
- Content snippets

### Step 2: Fetch

Use `mcp__uno__uno_platform_docs_fetch` to retrieve full content of high-value pages identified by search.

```
Fetch parameters:
- sourcePath: from search results SourcePath field (e.g., "articles/guides/overview.md")
- anchor: optional section fragment (e.g., "getting-started", "data-binding")
- maxChars: content limit (4000-8000 for most cases, up to 15000 for comprehensive guides)
```

### Workflow Example

```
Topic: "How to implement region-based navigation with Uno Extensions"

1. Search: mcp__uno__uno_platform_docs_search("Navigation Extensions region-based", topK=8)
   -> Returns multiple results including "Navigation Overview", "Region Navigation", etc.

2. Fetch: mcp__uno__uno_platform_docs_fetch(
     sourcePath="articles/external/uno.extensions/doc/Learn/Navigation/Overview.md",
     maxChars=8000)
   -> Returns full navigation documentation with code examples

3. Cite: Include source URL in response
```

### Routing Rules

The agent rules initialization provides topic-to-query mappings for common searches. Use these canonical queries when available:

| Topic | Canonical Search Query |
|-------|----------------------|
| Project setup / new project | `"dotnet new templates"` |
| MVUX / reactive / feeds | `"MVUX"` |
| Navigation / routing | `"Navigation"` |
| Styling / theming / resources | `"Styling and Theming"` |
| Data binding / MVVM | `"Data Binding and MVVM"` |
| Controls / layout | `"Controls and Layout"` |
| Hot Reload | `"Hot Reload"` |
| Platform-specific code | `"Platform-Specific Code"` |
| WebAssembly / WASM | `"WebAssembly"` |
| Dependency injection / DI | `"Dependency Injection and Services"` |
| Performance | `"Performance"` |
| Testing | `"Testing Uno Applications"` |
| Publishing / deployment | `"Publishing & Deployment"` |
| Troubleshooting | `"Troubleshooting Common Issues"` |
| IDE setup | `"IDE Setup"` |
| Responsive design / layouts | `"Responsive Design"` |
| Logging / diagnostics | `"Logging and Diagnostics"` |

---

## Citation Requirements

MCP results are external data fetched from the Uno Platform documentation server. Proper attribution is mandatory.

### Rules

1. **Always cite the source URL** from MCP results when presenting documentation content
2. **Never present fetched content as original knowledge.** MCP results come from external documentation and must be attributed
3. **Include the documentation page title** alongside the URL when available
4. **Distinguish between static skill content and MCP-fetched content.** Static content from SKILL.md files is part of this plugin; MCP content is external

### Citation Format

When presenting information from MCP results:

```
According to the Uno Platform documentation on [topic]:
[content from MCP]
Source: [URL from MCP result]
```

---

## Safety Guidelines

MCP results are external data and must be treated with appropriate caution.

### Validation Rules

1. **Validate code suggestions before acting.** MCP documentation may contain examples targeting different Uno Platform versions or configurations. Verify compatibility with the current project
2. **Check version alignment.** Ensure documentation references match the project's Uno Platform version (5.x vs 6.x) and .NET version
3. **Do not blindly apply code from MCP results.** Adapt examples to the project's architecture, Extension
Files: 1
Size: 14.8 KB
Complexity: 17/100
Category: AI Agents

Related in AI Agents