oh-my-claude-sisyphus 3.5.5 → 3.5.7

package/README.md

@@ -11,407 +11,122 @@
 
 **Multi-agent orchestration for Claude Code. Zero learning curve.**
 
-*Some advanced users customize zsh for years — most of us just use oh-my-zsh.*
 *Don't learn Claude Code. Just use OMC.*
 
-[Get Started](#get-started) • [Documentation](https://yeachan-heo.github.io/oh-my-claudecode-website) • [Migration Guide](docs/MIGRATION.md)
+[Get Started](#quick-start) • [Documentation](https://yeachan-heo.github.io/oh-my-claudecode-website) • [Migration Guide](docs/MIGRATION.md)
 
 </div>
 
 ---
 
-## Get Started (30 seconds)
+## Quick Start
 
-**Step 1:** Install the plugin
-```
+**Step 1: Install**
+```bash
 /plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
 /plugin install oh-my-claudecode
 ```
 
-**Step 2:** Run setup
-```
+**Step 2: Setup**
+```bash
 /oh-my-claudecode:omc-setup
 ```
 
-That's it. Everything else is automatic.
-
----
-
-## What Happens Now
-
-| When You... | I Automatically... |
-|-------------|-------------------|
-| Give me a complex task | Parallelize with specialist agents |
-| Say "plan this" | Start a planning interview |
-| Say "don't stop until done" | Persist until verified complete |
-| Work on UI/frontend | Activate design sensibility |
-| Need research or exploration | Delegate to specialized agents |
-| Say "build me..." or use autopilot | Execute full autonomous workflow |
-
-**You don't need to memorize commands.** I detect intent from natural language and activate the right behaviors automatically.
-
----
-
-## Magic Keywords (Optional Shortcuts)
-
-These are **optional shortcuts** for power users who want explicit control. Natural language works just fine - these keywords simply provide precision when you want it.
-
-Include these words anywhere in your message:
-
-| Keyword | Effect |
-|---------|--------|
-| `ralph` | Persistence mode - won't stop until done |
-| `ralplan` | Iterative planning with consensus |
-| `ulw` / `ultrawork` | Maximum parallel execution |
-| `ultrapilot` | Parallel autopilot (3-5x faster) |
-| `swarm` | N coordinated agents |
-| `pipeline` | Sequential agent chaining |
-| `eco` / `ecomode` | Token-efficient parallel execution |
-| `plan` | Start a planning interview |
-| `autopilot` / `ap` | Full autonomous execution |
-
-**Combine them:** `ralph ulw: migrate the database` or `eco: refactor auth system`
-
----
-
-## Execution Modes (v3.4.0)
-
-### Ultrapilot: Parallel Autopilot
-
-3-5x faster execution with up to 5 parallel workers. Perfect for multi-component systems and large refactoring:
-
-```
-/oh-my-claudecode:ultrapilot "build a fullstack todo app"
-```
-
-**How it works:**
-- Automatic task decomposition into parallelizable subtasks
-- Non-overlapping file ownership prevents conflicts
-- Parallel execution with intelligent coordination
-- Automatic conflict detection and resolution
-
----
-
-### Swarm: Coordinated Agents
-
-N independent agents claiming tasks from a shared pool:
-
-```
-/oh-my-claudecode:swarm 5:executor "fix all TypeScript errors"
-```
-
-**Features:**
-- Atomic task claiming prevents duplicate work
-- 5-minute timeout per task with auto-release
-- Scales from 2 to 10 workers
-
----
-
-### Pipeline: Sequential Chaining
-
-Chain agents together with data passing between stages:
-
-```
-/oh-my-claudecode:pipeline explore:haiku -> architect:opus -> executor:sonnet
-```
-
-**Built-in Presets:**
-- `review` - explore → architect → critic → executor
-- `implement` - planner → executor → tdd-guide
-- `debug` - explore → architect → build-fixer
-- `security` - explore → security-reviewer → executor
-
----
-
-### Ecomode: Token-Efficient
-
-Maximum parallelism with Haiku where possible, falling back to Sonnet/Opus for complex reasoning:
-
-```
-/oh-my-claudecode:ecomode "refactor the authentication system"
-```
-
-**30-50% token savings** compared to standard ultrawork while maintaining quality.
-
----
-
-## Auto Skill Learning (v3.5.0)
-
-OMC can automatically detect patterns in your problem-solving and suggest extracting them as reusable skills.
-
-### How It Works
-
-1. **Pattern Detection** - Recognizes problem-solution pairs in conversations
-2. **Skill Extraction** - `/oh-my-claudecode:learner` extracts reusable knowledge
-3. **Auto-Matching** - Fuzzy matching detects when skills apply to new problems
-4. **Auto-Invocation** - High-confidence matches (80+) auto-apply without prompting
-
-### Managing Local Skills
-
-```
-/oh-my-claudecode:skill list           # List all learned skills
-/oh-my-claudecode:skill search "auth"  # Find skills by keyword
-/oh-my-claudecode:skill edit <name>    # Edit a skill
-/oh-my-claudecode:skill sync           # Sync user + project skills
-```
-
-### Skill Storage
-
-- **User-level**: `~/.claude/skills/sisyphus-learned/` (shared across projects)
-- **Project-level**: `.omc/skills/` (project-specific)
-
-Skills use YAML frontmatter with triggers, tags, and quality scores.
-
----
-
-## Analytics & Cost Tracking (v3.5.0)
-
-Track your Claude Code usage across all sessions with automatic transcript analysis.
-
-### Backfill Historical Data
-
-```
-omc backfill                    # Analyze all transcripts
-omc backfill --from 2026-01-01  # From specific date
-omc backfill --project "*/myproject/*"  # Filter by project
-```
-
-### View Statistics
-
-```
-omc stats                       # All sessions aggregate
-omc stats --session             # Current session only
-omc stats --json                # JSON output
-```
-
-**Sample Output:**
-```
-📊 All Sessions Stats
-Sessions: 18
-Entries: 3356
-
-💰 Token Usage & Cost
-Total Tokens: 4.36M
-Total Cost: $2620.49
-
-🤖 Top Agents by Cost (All Sessions)
-  (main session)              700.7k tokens  $1546.46
-  oh-my-claudecode:architect    1.18M tokens  $432.68
-  oh-my-claudecode:planner    540.9k tokens  $274.85
-  oh-my-claudecode:executor   306.9k tokens  $77.43
-```
-
-**Features:**
-- Automatic backfill on first `omc stats` run
-- Global storage in `~/.omc/state/` (cross-project)
-- Proper agent attribution (main session vs spawned agents)
-- Deduplication prevents double-counting
-
----
-
-## Data Analysis & Research (v3.4.0)
-
-### Scientist Agent Tiers
-
-Three tiers of scientist agents for quantitative analysis and data science:
-
-| Agent | Model | Use For |
-|-------|-------|---------|
-| `scientist-low` | Haiku | Quick data inspection, simple statistics, file enumeration |
-| `scientist` | Sonnet | Standard analysis, pattern detection, visualization |
-| `scientist-high` | Opus | Complex reasoning, hypothesis validation, ML workflows |
-
-**Features:**
-- **Persistent Python REPL** - Variables persist across calls (no pickle/reload overhead)
-- **Structured markers** - `[FINDING]`, `[STAT:*]`, `[DATA]`, `[LIMITATION]` for parsed output
-- **Quality gates** - Every finding requires statistical evidence (CI, effect size, p-value)
-- **Auto-visualization** - Charts saved to `.omc/scientist/figures/`
-- **Report generation** - Markdown reports with embedded figures
-
-```python
-# Variables persist across calls!
-python_repl(action="execute", researchSessionID="analysis",
-            code="import pandas as pd; df = pd.read_csv('data.csv')")
-
-# df still exists - no need to reload
-python_repl(action="execute", researchSessionID="analysis",
-            code="print(df.describe())")
-```
-
-### /oh-my-claudecode:research Command (NEW)
-
-Orchestrate parallel scientist agents for comprehensive research workflows:
-
-```
-/oh-my-claudecode:research <goal>                    # Standard research with checkpoints
-/oh-my-claudecode:research AUTO: <goal>              # Fully autonomous until complete
-/oh-my-claudecode:research status                    # Check current session
-/oh-my-claudecode:research resume                    # Resume interrupted session
-/oh-my-claudecode:research list                      # List all sessions
-/oh-my-claudecode:research report <session-id>       # Generate report for session
-```
-
-**Research Protocol:**
-1. **Decomposition** - Breaks goal into 3-7 independent stages
-2. **Parallel Execution** - Fires scientist agents concurrently (max 5)
-3. **Cross-Validation** - Verifies consistency across findings
-4. **Synthesis** - Generates comprehensive markdown report
-
-**Smart Model Routing:**
-- Data gathering tasks → `scientist-low` (Haiku)
-- Standard analysis → `scientist` (Sonnet)
-- Complex reasoning → `scientist-high` (Opus)
-
-**Session Management:** Research state persists at `.omc/research/{session-id}/` enabling resume after interruption.
-
----
-
-## Stopping Things
-
-Just say:
-- "stop"
-- "cancel"
-- "abort"
-
-I'll intelligently determine what to stop based on context.
-
----
-
-## MCP Server Configuration
-
-Extend Claude Code with additional tools via Model Context Protocol (MCP) servers.
-
-```
-/oh-my-claudecode:mcp-setup
-```
-
-### Supported MCP Servers
-
-| Server | Description | API Key Required |
-|--------|-------------|------------------|
-| **Context7** | Documentation and code context from popular libraries | No |
-| **Exa** | Enhanced web search (replaces built-in websearch) | Yes |
-| **Filesystem** | Extended file system access | No |
-| **GitHub** | GitHub API for issues, PRs, repos | Yes (PAT) |
-
-### Quick Setup
-
-Run the setup command and follow the prompts:
-```
-/oh-my-claudecode:mcp-setup
+**Step 3: Build something**
 ```
-
-Or configure manually in `~/.claude/settings.json`:
-```json
-{
-  "mcpServers": {
-    "context7": {
-      "command": "npx",
-      "args": ["-y", "@upstash/context7-mcp"]
-    },
-    "exa": {
-      "command": "npx",
-      "args": ["-y", "exa-mcp-server"],
-      "env": {
-        "EXA_API_KEY": "your-key-here"
-      }
-    }
-  }
-}
+autopilot: build a REST API for managing tasks
 ```
 
-After configuration, restart Claude Code for changes to take effect.
+That's it. Everything else is automatic.
 
 ---
 
-## What's Under the Hood
+## Why oh-my-claudecode?
 
-- **32 Specialized Agents** - architect, researcher, explore, designer, writer, vision, critic, analyst, executor, planner, qa-tester, scientist (with tier variants including explore-high)
-- **40 Skills** - orchestrate, autopilot, ultrawork, ultrapilot, swarm, pipeline, ecomode, ralph, planner, ralplan, deepsearch, analyze, research, tdd, build-fix, code-review, security-review, git-master, frontend-ui-ux, learner, mcp-setup, cancel (unified), and more
-- **5 Execution Modes** - Autopilot (autonomous), Ultrapilot (3-5x parallel), Swarm (coordinated), Pipeline (sequential), Ecomode (token-efficient)
-- **MCP Server Support** - Easy configuration of Context7, Exa, GitHub, and custom MCP servers
-- **Persistent Python REPL** - True variable persistence for data analysis
-- **Research Workflow** - Parallel scientist orchestration with `/oh-my-claudecode:research` command
-- **HUD Statusline** - Real-time visualization of orchestration state
-- **Learned Skills** - Extract reusable insights from sessions with `/oh-my-claudecode:learner`
-- **Memory System** - Persistent context that survives compaction
+- **Zero configuration required** - Works out of the box with intelligent defaults
+- **Natural language interface** - No commands to memorize, just describe what you want
+- **Automatic parallelization** - Complex tasks distributed across specialized agents
+- **Persistent execution** - Won't give up until the job is verified complete
+- **Cost optimization** - Smart model routing saves 30-50% on tokens
+- **Learn from experience** - Automatically extracts and reuses problem-solving patterns
+- **Real-time visibility** - HUD statusline shows what's happening under the hood
 
 ---
 
-## HUD Statusline
+## Features
 
-The HUD displays real-time orchestration status in Claude Code's status bar:
+### Execution Modes
+Multiple strategies for different use cases - from fully autonomous builds to token-efficient refactoring. [Learn more →](https://yeachan-heo.github.io/oh-my-claudecode-website/execution-modes)
 
-```
-[OMC] | 5h:0% wk:100%(1d6h) | ctx:45% | agents:Ae
-todos:3/5 (working: Implementing feature)
-```
+| Mode | Speed | Use For |
+|------|-------|---------|
+| **Autopilot** | Fast | Full autonomous workflows |
+| **Ultrapilot** | 3-5x faster | Multi-component systems |
+| **Ecomode** | Fast + 30-50% cheaper | Budget-conscious projects |
+| **Swarm** | Coordinated | Parallel independent tasks |
+| **Pipeline** | Sequential | Multi-stage processing |
 
-**Line 1:** Core metrics
-- Rate limits with reset times (e.g., `wk:100%(1d6h)` = resets in 1 day 6 hours)
-- Context window usage
-- Active agents (coded by type and model tier)
+### Intelligent Orchestration
+- **32 specialized agents** for architecture, research, design, testing, data science
+- **Smart model routing** - Haiku for simple tasks, Opus for complex reasoning
+- **Automatic delegation** - Right agent for the job, every time
 
-**Line 2:** Todo progress
-- Completion ratio (`3/5`)
-- Current task in progress
+### Developer Experience
+- **Magic keywords** - `ralph`, `ulw`, `eco`, `plan` for explicit control
+- **HUD statusline** - Real-time orchestration metrics in your status bar
+- **Skill learning** - Extract reusable patterns from your sessions
+- **Analytics & cost tracking** - Understand token usage across all sessions
 
-Run `/oh-my-claudecode:hud setup` to configure display options.
+[Full feature list →](docs/REFERENCE.md)
 
 ---
 
-## Coming from 2.x?
+## Magic Keywords
 
-**Good news:** Your old commands still work!
+Optional shortcuts for power users. Natural language works fine without them.
 
-```
-/oh-my-claudecode:ralph "task"      →  Still works (or just say "ralph: task")
-/oh-my-claudecode:ultrawork "task"  →  Still works (or just use "ulw" keyword)
-/oh-my-claudecode:planner "task"    →  Still works (or just say "plan this")
-```
+| Keyword | Effect | Example |
+|---------|--------|---------|
+| `autopilot` | Full autonomous execution | `autopilot: build a todo app` |
+| `ralph` | Persistence mode | `ralph: refactor auth` |
+| `ulw` | Maximum parallelism | `ulw fix all errors` |
+| `eco` | Token-efficient execution | `eco: migrate database` |
+| `plan` | Planning interview | `plan the API` |
 
-The difference? You don't *need* them anymore. Everything auto-activates.
-
-See the [Migration Guide](docs/MIGRATION.md) for details.
+**Combine them:** `ralph ulw: migrate database` = persistence + parallelism
 
 ---
 
 ## Documentation
 
-- [Full Reference](docs/FULL-README.md) - Complete documentation (800+ lines)
-- [Migration Guide](docs/MIGRATION.md) - 2.x to 3.0 transition
-- [Architecture](docs/ARCHITECTURE.md) - Technical deep-dive
-- [Website](https://yeachan-heo.github.io/oh-my-claudecode-website) - Online docs
+- **[Full Reference](docs/REFERENCE.md)** - Complete feature documentation
+- **[Website](https://yeachan-heo.github.io/oh-my-claudecode-website)** - Interactive guides and examples
+- **[Migration Guide](docs/MIGRATION.md)** - Upgrade from v2.x
+- **[Architecture](docs/ARCHITECTURE.md)** - How it works under the hood
 
 ---
 
 ## Requirements
 
 - [Claude Code](https://docs.anthropic.com/claude-code) CLI
-- One of:
-  - **Claude Max/Pro subscription** (recommended for individuals)
-  - **Anthropic API key** (for API-based usage)
-
----
-
-## Star History
-
-[![Star History Chart](https://api.star-history.com/svg?repos=Yeachan-Heo/oh-my-claudecode&type=Date)](https://star-history.com/#Yeachan-Heo/oh-my-claudecode&Date)
+- Claude Max/Pro subscription OR Anthropic API key
 
 ---
 
 ## License
 
-MIT - see [LICENSE](LICENSE)
+MIT
 
 ---
 
 <div align="center">
 
-**Inspired by:**
-
-[oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/NexTechFusion/Superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code)
+**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/NexTechFusion/Superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code)
 
 **Zero learning curve. Maximum power.**
 
 </div>
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=Yeachan-Heo/oh-my-claudecode&type=date&legend=top-left)](https://www.star-history.com/#Yeachan-Heo/oh-my-claudecode&type=date&legend=top-left)

package/commands/mcp-setup.md

@@ -8,7 +8,7 @@ Configure Model Context Protocol (MCP) servers to extend Claude Code's capabilit
 
 ## Overview
 
-MCP servers provide additional tools that Claude Code agents can use. This skill helps you configure popular MCP servers using the `claude mcp add` command-line interface.
+MCP servers provide additional tools that Claude Code agents can use. This skill helps you configure popular MCP servers in your `~/.claude/settings.json`.
 
 ## Step 1: Show Available MCP Servers
 
@@ -54,51 +54,94 @@ Do you have a GitHub Personal Access Token?
 - Enter your token, or type 'skip' to configure later
 ```
 
-## Step 3: Add MCP Servers Using CLI
+## Step 3: Update settings.json
 
-Use the `claude mcp add` command to configure each MCP server. The CLI automatically handles settings.json updates and merging.
+Read the current `~/.claude/settings.json` and add/update the `mcpServers` section.
 
 ### Context7 Configuration:
-```bash
-claude mcp add context7 -- npx -y @upstash/context7-mcp
+```json
+{
+  "mcpServers": {
+    "context7": {
+      "command": "npx",
+      "args": ["-y", "@upstash/context7-mcp"]
+    }
+  }
+}
 ```
 
 ### Exa Web Search Configuration:
-```bash
-claude mcp add -e EXA_API_KEY=<user-provided-key> exa -- npx -y exa-mcp-server
+```json
+{
+  "mcpServers": {
+    "exa": {
+      "command": "npx",
+      "args": ["-y", "exa-mcp-server"],
+      "env": {
+        "EXA_API_KEY": "<user-provided-key>"
+      }
+    }
+  }
+}
 ```
 
 ### Filesystem Configuration:
-```bash
-claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem <allowed-directories>
+```json
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-filesystem", "<allowed-directories>"]
+    }
+  }
+}
 ```
 
 ### GitHub Configuration:
+```json
+{
+  "mcpServers": {
+    "github": {
+      "command": "docker",
+      "args": ["run", "-i", "--rm", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"],
+      "env": {
+        "GITHUB_PERSONAL_ACCESS_TOKEN": "<user-provided-token>"
+      }
+    }
+  }
+}
+```
+> Note: GitHub MCP requires Docker. Alternatively, configure as a remote URL: https://api.githubcopilot.com/mcp/
+
+## Step 4: Merge Configuration
+
+When updating settings.json:
+
+1. Read existing file: `~/.claude/settings.json`
+2. Parse as JSON (handle comments with jsonc-parser if needed)
+3. Merge new `mcpServers` entries with existing ones (don't overwrite user's other MCP servers)
+4. Write back to file with proper formatting
 
-**Option 1: Docker (local)**
 ```bash
-claude mcp add -e GITHUB_PERSONAL_ACCESS_TOKEN=<user-provided-token> github -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server
+# Backup existing settings first
+cp ~/.claude/settings.json ~/.claude/settings.json.bak 2>/dev/null || true
 ```
 
-**Option 2: HTTP (remote)**
-```bash
-claude mcp add --transport http github https://api.githubcopilot.com/mcp/
-```
+Use the Edit tool or Write tool to update the settings file, preserving existing configuration.
 
-> Note: Docker option requires Docker installed. HTTP option is simpler but may have different capabilities.
-
-## Step 4: Verify Installation
+## Step 5: Verify Installation
 
 After configuration, verify the MCP servers are properly set up:
 
 ```bash
-# List configured MCP servers
-claude mcp list
-```
+# Check if settings.json has mcpServers
+grep -q "mcpServers" ~/.claude/settings.json && echo "MCP servers configured" || echo "Configuration may have failed"
 
-This will display all configured MCP servers and their status.
+# List configured servers
+node -e "const s = require('$HOME/.claude/settings.json'); console.log('Configured MCP servers:', Object.keys(s.mcpServers || {}).join(', ') || 'none')"
+```
 
-## Step 5: Show Completion Message
+## Step 6: Show Completion Message
 
 ```
 MCP Server Configuration Complete!
@@ -109,7 +152,6 @@ CONFIGURED SERVERS:
 NEXT STEPS:
 1. Restart Claude Code for changes to take effect
 2. The configured MCP tools will be available to all agents
-3. Run `claude mcp list` to verify configuration
 
 USAGE TIPS:
 - Context7: Ask about library documentation (e.g., "How do I use React hooks?")
@@ -118,15 +160,11 @@ USAGE TIPS:
 - GitHub: Interact with GitHub repos, issues, and PRs
 
 TROUBLESHOOTING:
-- If MCP servers don't appear, run `claude mcp list` to check status
-- Ensure you have Node.js 18+ installed for npx-based servers
-- For GitHub Docker option, ensure Docker is installed and running
+- If MCP servers don't appear, check ~/.claude/settings.json for syntax errors
+- Ensure you have Node.js 18+ installed for npx commands
 - Run /oh-my-claudecode:doctor to diagnose issues
 
-MANAGING MCP SERVERS:
-- Add more servers: /oh-my-claudecode:mcp-setup or `claude mcp add ...`
-- List servers: `claude mcp list`
-- Remove a server: `claude mcp remove <server-name>`
+To add more MCP servers later, run: /oh-my-claudecode:mcp-setup
 ```
 
 ## Custom MCP Server
@@ -135,50 +173,23 @@ If user selects "Custom":
 
 Ask for:
 1. Server name (identifier)
-2. Transport type: `stdio` (default) or `http`
-3. For stdio: Command and arguments (e.g., `npx my-mcp-server`)
-4. For http: URL (e.g., `https://example.com/mcp`)
-5. Environment variables (optional, key=value pairs)
-6. HTTP headers (optional, for http transport only)
+2. Command to run (e.g., `npx`, `node`, path to executable)
+3. Arguments (comma-separated)
+4. Environment variables (optional, key=value pairs)
 
-Then construct and run the appropriate `claude mcp add` command:
-
-**For stdio servers:**
-```bash
-# Without environment variables
-claude mcp add <server-name> -- <command> [args...]
-
-# With environment variables
-claude mcp add -e KEY1=value1 -e KEY2=value2 <server-name> -- <command> [args...]
-```
-
-**For HTTP servers:**
-```bash
-# Basic HTTP server
-claude mcp add --transport http <server-name> <url>
-
-# HTTP server with headers
-claude mcp add --transport http --header "Authorization: Bearer <token>" <server-name> <url>
-```
+Then add to mcpServers section accordingly.
 
 ## Common Issues
 
 ### MCP Server Not Loading
 - Ensure Node.js 18+ is installed
 - Check that npx is available in PATH
-- Run `claude mcp list` to verify server status
-- Check server logs for errors
+- Verify no JSON syntax errors in settings.json
 
 ### API Key Issues
 - Exa: Verify key at https://dashboard.exa.ai
-- GitHub: Ensure token has required scopes (repo, read:org)
-- Re-run `claude mcp add` with correct credentials if needed
+- GitHub: Ensure token has required scopes
 
 ### Agents Still Using Built-in Tools
 - Restart Claude Code after configuration
 - The built-in websearch will be deprioritized when exa is configured
-- Run `claude mcp list` to confirm servers are active
-
-### Removing or Updating a Server
-- Remove: `claude mcp remove <server-name>`
-- Update: Remove the old server, then add it again with new configuration