mcp-prompt-optimizer 3.5.0 → 3.7.0

package/CHANGELOG.md

@@ -5,6 +5,26 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.6.0] - 2026-06-11
+
+### Fixed
+- Free-tier API key validation now works end-to-end. Free accounts (subscription_status NULL) can create one `sk-opt-*` key and use it with the MCP server for 7 LLM optimizations/month. Previously blocked by a bug where the free-tier launch patched an unused service module while the live enforcement layer retained the old 0-key/5-quota/none-MCP config.
+
+### Added
+- `connect` wizard: `npx mcp-prompt-optimizer connect` interactively adds your API key to Claude Desktop config. Supports macOS, Windows, and Linux config paths. Creates the server entry if absent, updates the key if the entry exists.
+- Upsell block in local fallback output: when no API key is configured, the rules-based result includes a one-command signup path (`npx mcp-prompt-optimizer connect`).
+
+## [3.5.0] - 2026-06-02
+
+### Added
+- LLM upsell block added to local fallback output
+- `connect` subcommand (interactive Claude Desktop config wizard)
+
+## [3.4.1] - 2026-05-28
+
+### Changed
+- Tier names updated from Explorer/Creator/Innovator to Free/Pro/Enterprise (D6 pricing migration)
+
 ## [3.4.0] - 2026-05-26
 
 ### Added

package/README.md

@@ -1,11 +1,11 @@
-# MCP Prompt Optimizer v3.1.3
+# MCP Prompt Optimizer v3.6.0
 
 [![NPM Version](https://img.shields.io/npm/v/mcp-prompt-optimizer)](https://www.npmjs.com/package/mcp-prompt-optimizer)
 [![License](https://img.shields.io/badge/license-Commercial-blue.svg)](LICENSE)
 [![CI](https://github.com/prompt-optimizer/mcp-prompt-optimizer/actions/workflows/ci.yml/badge.svg)](https://github.com/prompt-optimizer/mcp-prompt-optimizer/actions)
 [![Snyk Health](https://snyk.io/advisor/npm-package/mcp-prompt-optimizer/badge.svg)](https://snyk.io/advisor/npm-package/mcp-prompt-optimizer)
 
-🚀 **Professional cloud-based MCP server** for AI-powered prompt optimization with intelligent context detection, template management, team collaboration, and enterprise-grade reliability. Starting at $0/month.
+🚀 **Professional cloud-based MCP server** for AI-powered prompt optimization with intelligent context detection, template management, team collaboration, and enterprise-grade reliability. Starting at $0/month.
 
 
 
@@ -24,27 +24,34 @@
 
 ## 🚀 Quick Start
 
-**1. Get your API key (required):**
+**1. Get your API key:**
 
-- **🆓 Free Tier** (`sk-local-*`): 5 daily optimizations — [promptoptimizer.xyz/pricing](https://promptoptimizer.xyz/pricing)
-- **⭐ Paid Tiers** (`sk-opt-*`, `sk-team-*`): Higher quotas, team features, advanced capabilities
+- **🆓 Free Tier** (`sk-opt-*`): 7 LLM optimizations/month, 1 API key — no credit card required
+- **⭐ Pro** (`sk-opt-*`): 500 optimizations/month, full model config, Context Engineer
+- **🏢 Enterprise** (`sk-team-*`): Unlimited optimizations, team keys, shared quotas
+
+Sign up and generate your key at [promptoptimizer.xyz/dashboard](https://promptoptimizer.xyz/dashboard).
 
 **2. Install:**
 ```bash
 npm install -g mcp-prompt-optimizer
 ```
 
-**3. Configure your MCP client:**
+**3. Connect to Claude Desktop (one command):**
+```bash
+npx mcp-prompt-optimizer connect
+```
+This wizard reads your API key and writes the MCP server entry to Claude Desktop config automatically. Cross-platform (macOS, Windows, Linux).
 
-Add to `~/.claude/claude_desktop_config.json` (Claude Desktop):
+**Or configure manually** — add to `~/.claude/claude_desktop_config.json`:
 ```json
 {
   "mcpServers": {
-    "prompt-optimizer": {
+    "mcp-prompt-optimizer": {
       "command": "npx",
-      "args": ["mcp-prompt-optimizer"],
+      "args": ["-y", "mcp-prompt-optimizer"],
       "env": {
-        "OPTIMIZER_API_KEY": "sk-local-your-key-here"
+        "OPTIMIZER_API_KEY": "sk-opt-your-key-here"
       }
     }
   }
@@ -246,7 +253,7 @@ Real-time optimization status and AG-UI capabilities. Requires the feature to be
 
 ## 🤖 Context Engineer (CE) Tools
 
-Requires a Creator or Innovator subscription. CE tools generate agentic scaffolding artifacts (SOPs, skill packages, framework code) directly in your IDE.
+Requires a Pro or Enterprise subscription. CE tools generate agentic scaffolding artifacts (SOPs, skill packages, framework code) directly in your IDE.
 
 ### `generate_agent_sop`
 Generate a structured SOP document for an AI agent from a goal description. Returns markdown SOP ready for use.
@@ -269,6 +276,29 @@ Generate a complete skill package (SOP + SKILL.md + reference + examples + helpe
 ```
 `format` is one of `knowledge_doc` (default) or `agent_spec`.
 
+### `generate_harness_bundle`
+Generate a deployment-ready Agentic Harness ZIP bundle for a specific platform. Returns a confirmation when the bundle is queued for download.
+```json
+{
+  "goal": "The workflow goal the harness is built for",
+  "deploy_target": "claude_code",
+  "sop_content": "The SOP markdown content (required if no session_id)",
+  "session_id": "Optional: session ID from a prior generate_skill_package call"
+}
+```
+`deploy_target` accepts a single string (Pro+) or an array of strings (Enterprise — multi-platform simultaneously). Supported targets include `claude_code`, `langchain`, `autogen`, `crewai`, `amazon_q`, `aider`, `continue_dev`, and more. `amazon_q`, `aider`, `continue_dev`, `crewai` require Enterprise.
+
+### `explore_sop_approaches`
+Generate 3 parallel SOP variants (process-oriented, decision-tree, role-based) for comparison before committing to one. Returns an HTML comparison grid, a `variants` array, and a recommended variant. Enterprise required.
+```json
+{
+  "goal": "The workflow goal to generate SOP variants for",
+  "context": "Optional background context",
+  "blend_description": "Optional: blend all 3 variants into one SOP using this description"
+}
+```
+IntentFrame fields (`perspective`, `out_of_scope`, `success_definition`) are also accepted to scope the generation.
+
 ### `transform_for_framework`
 Transform a SOP into native code for your agent framework: LangChain tool, AutoGen agent, or Claude Code skill.
 ```json
@@ -290,7 +320,7 @@ Check your Context Engineer credit balance and what workflows are available at y
 Configure custom models in the WebUI and the MCP server uses them automatically.
 
 **Step 1 — Configure in WebUI:**
-1. Visit [Dashboard](https://promptoptimizer-blog.vercel.app/dashboard)
+1. Visit [Dashboard](https://promptoptimizer.xyz/dashboard)
 2. Go to Settings → User Settings
 3. Add your OpenRouter API key (from [openrouter.ai](https://openrouter.ai))
 4. Select your preferred models for optimization and evaluation
@@ -313,35 +343,36 @@ Configure custom models in the WebUI and the MCP server uses them automatically.
 | Code / technical | `anthropic/claude-3-5-sonnet` | `anthropic/claude-3-haiku` |
 
 > **Two different API keys:**
-> - **Service key** (`sk-opt-*`) — your MCP Prompt Optimizer subscription
+> - **Service key** (`sk-opt-*` or `sk-team-*`) — your MCP Prompt Optimizer subscription
 > - **OpenRouter key** — your personal OpenRouter account for model usage costs
 
 ---
 
 ## 💰 Subscription Plans
 
-| Plan | Price | Optimizations/month | CE Credits | Team members |
+| Plan | Price | Optimizations/month | CE Credits | API Keys |
 |---|---|---|---|---|
-| 🎯 Explorer | $2.99/mo | 20 | 5 | 1 |
-| 🎨 Creator | $29/mo | 18,000 | 30 | 2 + 1 key |
-| 🚀 Innovator | $99/mo | 75,000 | Unlimited | 5 + 10 keys |
-
-🆓 **Free trial:** 5 optimizations with full feature access.
+| 🆓 Free | $0 | 7 LLM | — | 1 |
+| ⭐ Pro | $19/mo | 500 | 5 | 1 |
+| 🏢 Enterprise | Custom | Unlimited | 50 | 10 (shared) |
 
 All plans include AI context detection, template management, personal model configuration, and optimization insights.
 
+[Get started free →](https://promptoptimizer.xyz/dashboard)
+
 ---
 
 ## 🔧 CLI Commands
 
 ```bash
-mcp-prompt-optimizer check-status   # Check API key and quota status
-mcp-prompt-optimizer validate-key   # Validate API key with backend
-mcp-prompt-optimizer test           # Test backend integration
-mcp-prompt-optimizer diagnose       # Run comprehensive diagnostic
-mcp-prompt-optimizer clear-cache    # Clear validation cache
-mcp-prompt-optimizer help           # Show help and setup instructions
-mcp-prompt-optimizer version        # Show version information
+npx mcp-prompt-optimizer connect        # Interactive wizard: add API key to Claude Desktop config
+mcp-prompt-optimizer check-status       # Check API key and quota status
+mcp-prompt-optimizer validate-key       # Validate API key with backend
+mcp-prompt-optimizer test               # Test backend integration
+mcp-prompt-optimizer diagnose           # Run comprehensive diagnostic
+mcp-prompt-optimizer clear-cache        # Clear validation cache
+mcp-prompt-optimizer help               # Show help and setup instructions
+mcp-prompt-optimizer version            # Show version information
 ```
 
 ---
@@ -355,7 +386,7 @@ mcp-prompt-optimizer version        # Show version information
 - Role-based access control
 
 ### Individual API Keys (`sk-opt-*`)
-- Personal quotas and billing
+- Personal quotas and billing — available on Free and Pro tiers
 - Individual template libraries
 - Account self-management
 
@@ -377,9 +408,9 @@ mcp-prompt-optimizer version        # Show version information
 ```json
 {
   "mcpServers": {
-    "prompt-optimizer": {
+    "mcp-prompt-optimizer": {
       "command": "npx",
-      "args": ["mcp-prompt-optimizer"],
+      "args": ["-y", "mcp-prompt-optimizer"],
       "env": { "OPTIMIZER_API_KEY": "sk-opt-your-key-here" }
     }
   }
@@ -391,9 +422,9 @@ Add to `~/.cursor/mcp.json`:
 ```json
 {
   "mcpServers": {
-    "prompt-optimizer": {
+    "mcp-prompt-optimizer": {
       "command": "npx",
-      "args": ["mcp-prompt-optimizer"],
+      "args": ["-y", "mcp-prompt-optimizer"],
       "env": { "OPTIMIZER_API_KEY": "sk-opt-your-key-here" }
     }
   }
@@ -407,6 +438,29 @@ Windsurf, Cline, VS Code, Zed, Replit, JetBrains IDEs, and Neovim are all suppor
 
 ## 📦 Changelog
 
+### v3.6.0
+- **Free tier MCP access** — Free users can now create an API key (`sk-opt-*`) and use the MCP server for 7 LLM optimizations/month at no cost. Previously, key creation was blocked in the live service due to a bug introduced when the free-tier launch landed in an unused module. Keys with `subscription_status: NULL` (all free accounts) now validate correctly.
+- **`connect` wizard** — `npx mcp-prompt-optimizer connect` interactively writes your API key to Claude Desktop config on macOS, Windows, and Linux. Replaces manual JSON editing for new users.
+- **Upsell block** — Local rules fallback output now includes a concise upgrade prompt with a one-command onboarding path when no API key is configured.
+
+### v3.5.0
+- LLM upsell block added to local fallback output
+- `connect` subcommand added (interactive Claude Desktop config wizard)
+
+### v3.4.1
+- Tier names migrated from Explorer/Creator/Innovator to Free/Pro/Enterprise (D6 pricing)
+
+### v3.4.0
+- `explore_sop_approaches` tool: generates 3 parallel SOP variants (process-oriented, decision-tree, role-based) for comparison before committing. Optionally accepts `blend_description` to blend variants directly. Enterprise tier required.
+
+### v3.3.0
+- `generate_harness_bundle` tool: generates deployment-ready ZIP harness for 14+ platforms. Single deploy target (Pro+) or multi-platform array (Enterprise).
+- Intent frame fields (`perspective`, `out_of_scope`, `success_definition`) added to `generate_agent_sop` for scoped SOP generation.
+
+### v3.2.x
+- `transform_for_framework` tool: converts SOP to native LangChain tool, AutoGen agent, or Claude Code skill
+- CE harness HTML review layer with interactive DAG visualization
+
 ### v3.0.3
 - **Rules fallback output rewritten** — local optimization now produces user-facing prose prompts instead of raw XML scaffolding. The output is directly usable as a prompt without modification.
 - **All 18 local templates reworded** — template principles are now phrased as user request guidance rather than AI-assistant directives, producing more natural and actionable structured prompts.
@@ -429,9 +483,9 @@ Windsurf, Cline, VS Code, Zed, Replit, JetBrains IDEs, and Neovim are all suppor
 
 ## 🛠️ Support & Resources
 
-- 📖 **Documentation:** [promptoptimizer-blog.vercel.app/docs](https://promptoptimizer-blog.vercel.app/docs)
-- 📊 **Dashboard & model config:** [promptoptimizer-blog.vercel.app/dashboard](https://promptoptimizer-blog.vercel.app/dashboard)
-- 🚀 **Pricing & API Keys**: [promptoptimizer.xyz/local-license](https://promptoptimizer.xyz/local-license)
+- 📖 **Documentation:** [promptoptimizer.xyz/docs](https://promptoptimizer.xyz/docs)
+- 📊 **Dashboard & model config:** [promptoptimizer.xyz/dashboard](https://promptoptimizer.xyz/dashboard)
+- 🚀 **Pricing & API Keys**: [promptoptimizer.xyz/pricing](https://promptoptimizer.xyz/pricing)
 - 🐛 **Issues:** [GitHub Issues](https://github.com/prompt-optimizer/mcp-prompt-optimizer/issues)
 - 📄 **License:** [Commercial License](LICENSE)
 - 🔒 **Security:** [Security Policy](SECURITY.md)
@@ -440,8 +494,6 @@ Windsurf, Cline, VS Code, Zed, Replit, JetBrains IDEs, and Neovim are all suppor
 - 📝 **Changelog:** [Release History](CHANGELOG.md)
 - 📧 **Email support:** support@promptoptimizer.xyz
 
-
 ---
 
-*Get started with 5 free optimizations at [promptoptimizer.xyz/pricing](https://promptoptimizer.xyz/pricing)*
-at [promptoptimizer.xyz/pricing](https://promptoptimizer.xyz/pricing)*
+*Start free at [promptoptimizer.xyz](https://promptoptimizer.xyz) — 7 LLM optimizations/month, no credit card required.*

package/index.js

@@ -1464,11 +1464,9 @@ class MCPPromptOptimizer {
       output += `**Template:** \`${result.template_used || 'general'}\`\n\n`;
       output += `**Optimized Prompt:**\n\`\`\`\n${result.optimized_prompt}\n\`\`\`\n\n`;
     } else if (result.fallback_mode) {
-      // Legacy path — should no longer be reached
-      output = `# ⚠️ Backend Unavailable — Prompt Not Optimized\n\n`;
-      output += `**Issue:** ${result.error_reason}\n`;
-      output += `The backend could not be reached. Your original prompt is returned below unmodified.\n\n`;
-      output += `**Original Prompt:**\n\`\`\`\n${result.optimized_prompt}\n\`\`\`\n\n`;
+      output = `# 🔧 Optimized (local rules — backend slow)\n\n`;
+      output += `*Backend unavailable this time — applied local rule templates. Try again for LLM optimization.*\n\n`;
+      output += `**Optimized Prompt:**\n\`\`\`\n${result.optimized_prompt}\n\`\`\`\n\n`;
     } else {
       output = `# 🎯 Optimized Prompt\n\n${result.optimized_prompt}\n\n`;
       if (result.confidence_score < 0.25) {
@@ -1481,7 +1479,7 @@ class MCPPromptOptimizer {
     } else {
       output += `**Confidence:** ${(result.confidence_score * 100).toFixed(1)}%\n`;
     }
-    output += `**AI Context:** ${context.detectedContext}\n`;
+    output += `**AI Context:** ${result.metadata?.context_detection?.ai_context || context.detectedContext}\n`;
     
     if (result.template_saved) {
       output += `\n📁 **Template Auto-Save**\n✅ Automatically saved as template (ID: \`${result.template_id}\`)\n*Confidence threshold: >70% required for auto-save*\n`;
@@ -1541,6 +1539,21 @@ class MCPPromptOptimizer {
     }
     
     if (!result.fallback_mode) {
+      if (result.quota_used != null) {
+        if (result.quota_limit == null) {
+          // Unlimited plan — show status only, no upsell
+          output += `\n📊 **Usage:** ${result.quota_used} optimizations — ✓ Unlimited plan\n`;
+        } else {
+          const remaining = result.quota_limit - result.quota_used;
+          if (result.quota_used >= result.quota_limit) {
+            output += `\n📊 **Usage:** ${result.quota_used}/${result.quota_limit} — quota reached. **[Upgrade for more →](https://promptoptimizer.xyz/pricing)**\n`;
+          } else if (remaining <= 2) {
+            output += `\n📊 **Usage:** ${result.quota_used}/${result.quota_limit} LLM optimizations (${remaining} left) — [Upgrade for more](https://promptoptimizer.xyz/pricing)\n`;
+          } else {
+            output += `\n📊 **Usage:** ${result.quota_used}/${result.quota_limit} LLM optimizations this month — [Upgrade for more](https://promptoptimizer.xyz/pricing)\n`;
+          }
+        }
+      }
       output += `\n🔗 **Quick Actions**\n- Dashboard: https://promptoptimizer.xyz/dashboard\n- Analytics: https://promptoptimizer.xyz/analytics\n`;
     } else {
       const confPct = Math.round((result.confidence_score || 0) * 100);
@@ -1805,67 +1818,162 @@ async function runConnectWizard() {
   const path = require('path');
   const os = require('os');
 
-  const configPaths = {
-    win32:  path.join(os.homedir(), 'AppData', 'Roaming', 'Claude', 'claude_desktop_config.json'),
-    darwin: path.join(os.homedir(), 'Library', 'Application Support', 'Claude', 'claude_desktop_config.json'),
-    linux:  path.join(os.homedir(), '.config', 'Claude', 'claude_desktop_config.json'),
-  };
-  const configPath = configPaths[process.platform] || configPaths.linux;
+  // Known MCP client config locations keyed by [client, platform]
+  const CLIENT_CONFIGS = [
+    {
+      name: 'Claude Desktop',
+      paths: {
+        win32:  path.join(os.homedir(), 'AppData', 'Roaming', 'Claude', 'claude_desktop_config.json'),
+        darwin: path.join(os.homedir(), 'Library', 'Application Support', 'Claude', 'claude_desktop_config.json'),
+        linux:  path.join(os.homedir(), '.config', 'Claude', 'claude_desktop_config.json'),
+      },
+      serverKey: 'mcp-prompt-optimizer',
+    },
+    {
+      name: 'Cursor',
+      paths: {
+        win32:  path.join(os.homedir(), '.cursor', 'mcp.json'),
+        darwin: path.join(os.homedir(), '.cursor', 'mcp.json'),
+        linux:  path.join(os.homedir(), '.cursor', 'mcp.json'),
+      },
+      serverKey: 'mcp-prompt-optimizer',
+    },
+    {
+      name: 'VS Code Cline / Roo',
+      paths: {
+        win32:  path.join(os.homedir(), 'AppData', 'Roaming', 'Code', 'User', 'globalStorage', 'saoudrizwan.claude-dev', 'settings', 'cline_mcp_settings.json'),
+        darwin: path.join(os.homedir(), 'Library', 'Application Support', 'Code', 'User', 'globalStorage', 'saoudrizwan.claude-dev', 'settings', 'cline_mcp_settings.json'),
+        linux:  path.join(os.homedir(), '.config', 'Code', 'User', 'globalStorage', 'saoudrizwan.claude-dev', 'settings', 'cline_mcp_settings.json'),
+      },
+      serverKey: 'mcp-prompt-optimizer',
+    },
+    {
+      name: 'Continue.dev',
+      paths: {
+        win32:  path.join(os.homedir(), '.continue', 'config.json'),
+        darwin: path.join(os.homedir(), '.continue', 'config.json'),
+        linux:  path.join(os.homedir(), '.continue', 'config.json'),
+      },
+      serverKey: 'mcp-prompt-optimizer',
+    },
+  ];
+
+  function safeWriteConfig(filePath, newConfig) {
+    const backupPath = filePath + '.bak';
+    // Backup
+    if (fs.existsSync(filePath)) {
+      fs.copyFileSync(filePath, backupPath);
+    }
+    try {
+      const serialized = JSON.stringify(newConfig, null, 2);
+      fs.writeFileSync(filePath, serialized, 'utf8');
+      // Verify round-trip
+      JSON.parse(fs.readFileSync(filePath, 'utf8'));
+    } catch (e) {
+      // Restore backup on any failure
+      if (fs.existsSync(backupPath)) {
+        fs.copyFileSync(backupPath, filePath);
+      }
+      throw e;
+    }
+  }
+
+  function patchConfig(config, serverKey, apiKey) {
+    if (!config.mcpServers) config.mcpServers = {};
+    if (config.mcpServers[serverKey]) {
+      if (!config.mcpServers[serverKey].env) config.mcpServers[serverKey].env = {};
+      config.mcpServers[serverKey].env.OPTIMIZER_API_KEY = apiKey;
+    } else {
+      config.mcpServers[serverKey] = {
+        command: 'npx',
+        args: ['-y', 'mcp-prompt-optimizer'],
+        env: { OPTIMIZER_API_KEY: apiKey },
+      };
+    }
+    return config;
+  }
 
   console.log('\n🔌 Prompt Optimizer — Connect Wizard\n');
 
-  if (!fs.existsSync(configPath)) {
-    console.log('❌ Claude Desktop config not found at:');
-    console.log(`   ${configPath}`);
-    console.log('\nOpen Claude Desktop first to create the config file, then re-run this command.');
+  // Detect which clients are installed
+  const platform = process.platform;
+  const found = CLIENT_CONFIGS
+    .map(c => ({ ...c, configPath: c.paths[platform] || c.paths.linux }))
+    .filter(c => fs.existsSync(c.configPath));
+
+  if (found.length === 0) {
+    console.log('❌ No supported MCP client config found. Supported clients:');
+    CLIENT_CONFIGS.forEach(c => {
+      const p = c.paths[platform] || c.paths.linux;
+      console.log(`   ${c.name}: ${p}`);
+    });
+    console.log('\nOpen your MCP client first to create its config file, then re-run this command.');
     process.exit(1);
   }
 
-  let config;
-  try {
-    config = JSON.parse(fs.readFileSync(configPath, 'utf8'));
-  } catch (e) {
-    console.log(`❌ Could not read config: ${e.message}`);
-    process.exit(1);
+  const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
+
+  function askApiKey(cb) {
+    rl.question('Paste your API key (get one free at https://promptoptimizer.xyz/dashboard): ', (key) => {
+      cb((key || '').trim());
+    });
   }
-  if (!config.mcpServers) config.mcpServers = {};
 
-  const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
-  rl.question('Paste your API key (get one free at https://promptoptimizer.xyz/dashboard): ', (apiKey) => {
+  function askClient(clients, cb) {
+    console.log('Multiple MCP clients detected. Which one should be configured?');
+    clients.forEach((c, i) => console.log(`  ${i + 1}) ${c.name}`));
+    rl.question('Enter number (or press Enter for all): ', (ans) => {
+      const n = parseInt(ans, 10);
+      if (!ans.trim()) {
+        cb(clients);
+      } else if (n >= 1 && n <= clients.length) {
+        cb([clients[n - 1]]);
+      } else {
+        console.log('Invalid selection, configuring all.');
+        cb(clients);
+      }
+    });
+  }
+
+  function applyToClients(clients, apiKey) {
     rl.close();
-    apiKey = (apiKey || '').trim();
+    let ok = 0;
+    for (const client of clients) {
+      let config;
+      try {
+        config = JSON.parse(fs.readFileSync(client.configPath, 'utf8'));
+      } catch (e) {
+        console.log(`❌ Could not read ${client.name} config: ${e.message}`);
+        continue;
+      }
+      try {
+        const patched = patchConfig(config, client.serverKey, apiKey);
+        safeWriteConfig(client.configPath, patched);
+        console.log(`✅ ${client.name} — configured (${client.configPath})`);
+        ok++;
+      } catch (e) {
+        console.log(`❌ Could not write ${client.name} config: ${e.message}`);
+        console.log('   Try running as administrator, or edit the file manually.');
+      }
+    }
+    if (ok > 0) {
+      console.log('\n👉 Restart your MCP client(s) to activate LLM optimization.');
+      console.log('   Free plan: 7 LLM optimizations/month.');
+      console.log('   Upgrade at https://promptoptimizer.xyz/pricing\n');
+    }
+  }
 
+  askApiKey((apiKey) => {
     if (!apiKey.startsWith('sk-')) {
+      rl.close();
       console.log('\n❌ Invalid key — must start with "sk-". Get one at https://promptoptimizer.xyz/dashboard');
       process.exit(1);
     }
-
-    const serverName = 'mcp-prompt-optimizer';
-    if (config.mcpServers[serverName]) {
-      if (!config.mcpServers[serverName].env) config.mcpServers[serverName].env = {};
-      config.mcpServers[serverName].env.OPTIMIZER_API_KEY = apiKey;
-      console.log(`\n✅ Updated "${serverName}" entry with your API key.`);
+    if (found.length === 1) {
+      applyToClients(found, apiKey);
     } else {
-      config.mcpServers[serverName] = {
-        command: 'npx',
-        args: ['-y', 'mcp-prompt-optimizer'],
-        env: { OPTIMIZER_API_KEY: apiKey },
-      };
-      console.log(`\n✅ Added "${serverName}" to Claude Desktop config.`);
+      askClient(found, (chosen) => applyToClients(chosen, apiKey));
     }
-
-    try {
-      fs.writeFileSync(configPath, JSON.stringify(config, null, 2), 'utf8');
-    } catch (e) {
-      console.log(`\n❌ Could not write config: ${e.message}`);
-      console.log('Try running as administrator, or edit the file manually.');
-      process.exit(1);
-    }
-
-    console.log(`   Config: ${configPath}`);
-    console.log('\n👉 Restart Claude Desktop to activate LLM optimization.');
-    console.log('   Free plan: 7 LLM optimizations/month.');
-    console.log('   Upgrade at https://promptoptimizer.xyz/pricing\n');
   });
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-prompt-optimizer",
-  "version": "3.5.0",
+  "version": "3.7.0",
   "description": "Professional cloud-based MCP server for AI-powered prompt optimization with intelligent context detection, Bayesian optimization, AG-UI real-time optimization, template auto-save, optimization insights, personal model configuration via WebUI, team collaboration, enterprise-grade features, production resilience, and startup validation. Universal compatibility with Claude Desktop, Cursor, Windsurf, and 17+ MCP clients.",
   "main": "index.js",
   "bin": {