#### Method 1: Using Claude's Official Tool
``bash
npx @claude/create-mcp-server


Select "ultimate-mcp-server" from the list

#### Method 2: Manual Configuration
1. Open Claude Desktop settings
2. Navigate to Developer → Model Context Protocol
3. Click "Add Server" and enter:
- Name: ultimate
- Command: npx
- Arguments: ultimate-mcp-server

#### Method 3: Edit Configuration File
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
`json
{
"mcpServers": {
"ultimate": {
"command": "npx",
"args": ["ultimate-mcp-server"],
"env": {
"OPENROUTER_API_KEY": "your-key-here"
}
}
}
}
`


#### Quick Install (Recommended)
`bash
claude mcp add ultimate npx ultimate-mcp-server
`

#### With API Keys
`bash
claude mcp add ultimate npx ultimate-mcp-server \
-e OPENROUTER_API_KEY=your-key \
-e ANTHROPIC_API_KEY=your-key \
-e GOOGLE_API_KEY=your-key
`

#### Local Development
`bash


Clone and build

#### Verify Installation
`bash
claude mcp list


Should show: ultimate: npx ultimate-mcp-server - ✓ Connected

1. Open Cursor Settings (Cmd/Ctrl + ,)
2. Search for "MCP" or navigate to Features → MCP
3. Click "Add MCP Server"
4. Configure:

`json
{
"name": "ultimate",
"command": "npx",
"args": ["ultimate-mcp-server"],
"env": {
"OPENROUTER_API_KEY": "your-key-here"
}
}
`

5. Restart Cursor to activate

Alternative: Direct Config Edit

Edit ~/.cursor/config/settings.json:
`json
{
"mcp": {
"servers": {
"ultimate": {
"command": "npx",
"args": ["ultimate-mcp-server"],
"env": {
"OPENROUTER_API_KEY": "your-key"
}
}
}
}
}
`


1. Install Continue extension from VS Code marketplace
2. Open Continue settings (Cmd/Ctrl + Shift + P → "Continue: Open Settings")
3. Add MCP configuration:

`json
{
"models": [...],
"mcpServers": {
"ultimate": {
"command": "npx",
"args": ["ultimate-mcp-server"],
"env": {
"OPENROUTER_API_KEY": "your-key"
}
}
}
}
`

4. Reload VS Code window


`yaml
name: ultimate
command: npx
args:
- ultimate-mcp-server
env:
OPENROUTER_API_KEY: your-key
`

5. Save and restart Windsurf


Add to ~/.cline/config.json:
`json
{
"mcpServers": {
"ultimate": {
"command": "npx",
"args": ["ultimate-mcp-server"],
"env": {
"OPENROUTER_API_KEY": "your-key"
}
}
}
}
`


`json
{
"ultimate": {
"command": "npx",
"args": ["ultimate-mcp-server"],
"transport": "stdio"
}
}
`


| Provider | Environment Variable | Get API Key | Models |
|----------|---------------------|-------------|---------|
| OpenRouter | OPENROUTER_API_KEY | Get Key | All 50+ models |
| Anthropic | ANTHROPIC_API_KEY | Get Key | Claude models |
| OpenAI | OPENAI_API_KEY | Get Key | GPT models |
| Google | GOOGLE_API_KEY | Get Key | Gemini models |
| Perplexity | PERPLEXITY_API_KEY | Get Key | Online search |

$3

#### Method 1: Environment Variables
`bash
export OPENROUTER_API_KEY="sk-or-..."
export ANTHROPIC_API_KEY="sk-ant-..."
`

#### Method 2: .env File
Create .env in your project:
`env
OPENROUTER_API_KEY=sk-or-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_API_KEY=...
`

#### Method 3: MCP Configuration
Add to your MCP client config:
`json
{
"env": {
"OPENROUTER_API_KEY": "your-key",
"ANTHROPIC_API_KEY": "your-key"
}
}
`


#### Ask AI
`typescript
// In your MCP client
await callTool('ask', {
prompt: 'Explain async/await in JavaScript',
model: 'openai/gpt-4o'
});
`

#### Analyze Error
`typescript
await callTool('analyze_error', {
error: 'TypeError: Cannot read property "x" of undefined',
language: 'javascript'
});
`

#### Generate Code
`typescript
await callTool('generate_code', {
description: 'Binary search algorithm',
language: 'python',
includeTests: true
});
`

#### Analyze Large Codebase
`typescript
await callTool('analyze_large_codebase', {
rootDir: './src',
query: 'Find all API endpoints',
pattern: '.*\\.(ts|js)$'
});
`


- ask - Query specific AI models
- orchestrate - Multi-model orchestration
- generate_code - AI code generation
- explain_code - Code explanation
- suggest_optimizations - Performance optimization
- debugging_session - Interactive debugging
- analyze_error - Error analysis
- analyze_codebase - Codebase analysis
- find_in_codebase - Pattern search
- get_metrics - Performance metrics


- analyze_large_codebase - Analyze with 1M+ tokens
- generate_directory_tree - Visual directory structure
- collect_code_context - Context collection
- analyze_project_structure - Architecture analysis
- find_codebase_patterns - Pattern detection
- generate_project_docs - Auto documentation
- estimate_analysis_cost - Cost estimation


- rag_ingest_document - Document ingestion
- rag_search - Semantic search
- rag_query - Q&A with sources
- build_knowledge_graph - Graph construction
- cognitive_search - Memory search
- build_memory_context - Context building
- get_related_memories - Related concepts
- export_knowledge_graph - Graph export


- analyze_ui_design - UI/UX analysis
- extract_design_system - Design tokens
- check_ui_accessibility - WCAG compliance
- compare_ui_designs - A/B comparison
- suggest_ui_improvements - UX suggestions
- analyze_ui_components - Component audit
- create_ui_style_guide - Style documentation
- analyze_user_flow - Journey mapping
- browser_navigate - Web navigation
- browser_screenshot - Page capture


- universal_search - Multi-provider search
- search_files - File search
- search_content - Content grep
- search_processes - Process search
- search_everything - Unified search