SuperClaude/superclaude/mcp/MCP_Sequential.md

# Sequential MCP Server

**Purpose**: Multi-step reasoning engine for complex analysis and systematic problem solving

## Triggers
- Complex debugging scenarios with multiple layers
- Architectural analysis and system design questions
- `--think`, `--think-hard`, `--ultrathink` flags
- Problems requiring hypothesis testing and validation
- Multi-component failure investigation
- Performance bottleneck identification requiring methodical approach

## Choose When
- **Over native reasoning**: When problems have 3+ interconnected components
- **For systematic analysis**: Root cause analysis, architecture review, security assessment
- **When structure matters**: Problems benefit from decomposition and evidence gathering
- **For cross-domain issues**: Problems spanning frontend, backend, database, infrastructure
- **Not for simple tasks**: Basic explanations, single-file changes, straightforward fixes

## Works Best With
- **Context7**: Sequential coordinates analysis → Context7 provides official patterns
- **Magic**: Sequential analyzes UI logic → Magic implements structured components
- **Playwright**: Sequential identifies testing strategy → Playwright executes validation

## Examples
```
"why is this API slow?" → Sequential (systematic performance analysis)
"design a microservices architecture" → Sequential (structured system design)
"debug this authentication flow" → Sequential (multi-component investigation)
"analyze security vulnerabilities" → Sequential (comprehensive threat modeling)
"explain this function" → Native Claude (simple explanation)
"fix this typo" → Native Claude (straightforward change)
```