mcp-prompt-optimizer 3.7.3 → 3.7.5

package/CHANGELOG.md

@@ -5,6 +5,24 @@ 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).
 
+## [3.7.5] - 2026-07-18
+
+### Fixed
+- **10 MCP tools were unconditionally broken**: `generate_agent_sop`, `transform_for_framework`, `generate_harness_bundle`, `explore_sop_approaches`, `get_prompt_by_slug`, `compile_prompt`, `list_template_versions`, `rollback_template`, `publish_template`, and `run_quick_evaluation` all called backend routes that only accepted a JWT — a credential this stdio client can never obtain (no browser, no login flow). Every call to these tools failed with an auth error, always. Backend now accepts API-key auth on these routes; verified the fix doesn't expand what a key is authorized to do (every route is scoped to the calling account's own data, same as routes that already worked).
+- **Tier-upgrade messages never fired**: the 403-detection check looked for the literal string `'403'` inside the error body, which never appears there — only the HTTP status code carries it. Now checks the real status code, so upgrade prompts actually show up when a real tier gate is hit.
+- **Fabricated fallback data**: `get_optimization_insights` and `get_real_time_status` silently returned hardcoded fake numbers (fake optimization counts, fake AG-UI metrics) on any backend error, indistinguishable from real account data. Both now say the data is unavailable instead of inventing it.
+- **`formatRealTimeStatus` read the wrong fields**: it never matched the AG-UI status endpoint's actual response shape, even when the call succeeded.
+- **`formatQuotaStatus` invented a fake `5000` quota limit** when the backend didn't report one.
+- **Free-tier quota text said 7/month**; the real limit is 20.
+- **Dead domain and wrong key-format references**: `promptoptimizer-blog.vercel.app` no longer resolves; some messages also claimed `sk-local-*` was a valid key format for this package (that's the sibling local package's prefix, not this one's).
+
+## [3.7.4] - 2026-07-16
+
+### Fixed
+- **CLI commands were mostly non-functional**: the README documented 8 `mcp-prompt-optimizer <command>` subcommands, but the argv dispatcher only ever recognized `connect`. Running any of `check-status`, `validate-key`, `diagnose`, `clear-cache`, `help`, or `version` silently started the blocking stdio MCP server instead, hanging the terminal. All six are now wired to their existing `lib/*.js` implementations.
+- **Unrecognized commands no longer fall through to the server.** Any argument that isn't a known command now prints an error and usage to stderr and exits 1, instead of silently starting the MCP server. This closes the bug class for future commands too, not just the six fixed here.
+- **Dropped `test` from the documented CLI commands.** It mapped to `tests/test-runner.js`, a maintainer-only pre-publish validation script that isn't included in the published npm package (`tests/` is not in `files`), so it could never have worked for an end user.
+
 ## [3.7.3] - 2026-07-16
 
 ### Fixed

package/README.md

@@ -368,7 +368,6 @@ All plans include AI context detection, template management, personal model conf
 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

package/index.js

@@ -1056,31 +1056,7 @@ class MCPPromptOptimizer {
       return { content: [{ type: "text", text: this.formatOptimizationInsights(result) }] };
       
     } catch (error) {
-      // Fallback to mock insights
-      const mockInsights = {
-        bayesian_status: {
-          optimization_active: true,
-          total_optimizations: 47,
-          improvement_rate: '23.5%',
-          confidence_score: 0.89
-        },
-        parameter_insights: {
-          most_effective_goals: ['clarity', 'technical_accuracy', 'analytical_depth'],
-          context_performance: {
-            'code_generation': 0.92,
-            'llm_interaction': 0.87,
-            'technical_automation': 0.84
-          },
-          optimization_trends: 'Steady improvement in technical contexts'
-        },
-        recommendations: args.include_recommendations !== false ? [
-          'Focus on technical_accuracy for code generation prompts',
-          'Combine clarity with analytical_depth for best results',
-          'Consider using structured_output context for data tasks'
-        ] : []
-      };
-
-      return { content: [{ type: "text", text: this.formatOptimizationInsights(mockInsights) }] };
+      return { content: [{ type: "text", text: `🧠 Optimization insights are unavailable right now (${error.message}). This is not your data — no insights were generated.` }] };
     }
   }
 
@@ -1095,22 +1071,7 @@ class MCPPromptOptimizer {
       return { content: [{ type: "text", text: this.formatRealTimeStatus(result) }] };
       
     } catch (error) {
-      const mockStatus = {
-        agui_status: 'available',
-        streaming_optimization: true,
-        websocket_support: true,
-        real_time_analytics: true,
-        active_optimizations: 3,
-        average_response_time: '1.2s',
-        features: {
-          live_optimization: true,
-          collaborative_editing: true,
-          instant_feedback: true,
-          performance_monitoring: true
-        }
-      };
-
-      return { content: [{ type: "text", text: this.formatRealTimeStatus(mockStatus) }] };
+      return { content: [{ type: "text", text: `⚡ AG-UI real-time status is unavailable right now (${error.message}).` }] };
     }
   }
 
@@ -1434,8 +1395,8 @@ class MCPPromptOptimizer {
         }]
       };
     } catch (error) {
-      if (error.message && error.message.includes('403')) {
-        return { content: [{ type: "text", text: "Error: SOP exploration requires Innovator tier. Upgrade at /pricing." }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Error: SOP exploration requires Innovator tier. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to explore SOP approaches: ${error.message}`);
     }
@@ -1450,9 +1411,8 @@ class MCPPromptOptimizer {
       output += `**Body:**\n\`\`\`\n${result.optimized_prompt || result.body || ''}\n\`\`\`\n`;
       return { content: [{ type: "text", text: output }] };
     } catch (error) {
-      const msg = error.message || '';
-      if (msg.includes('403') || msg.includes('TIER')) {
-        return { content: [{ type: "text", text: `Upgrade required: runtime prompt delivery requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${msg}` }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Upgrade required: runtime prompt delivery requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to fetch prompt by slug: ${error.message}`);
     }
@@ -1465,9 +1425,8 @@ class MCPPromptOptimizer {
       const compiled = result.compiled_prompt || result.body || JSON.stringify(result, null, 2);
       return { content: [{ type: "text", text: `# Compiled Prompt\n\n\`\`\`\n${compiled}\n\`\`\`\n` }] };
     } catch (error) {
-      const msg = error.message || '';
-      if (msg.includes('403') || msg.includes('TIER')) {
-        return { content: [{ type: "text", text: `Upgrade required: prompt compilation requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${msg}` }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Upgrade required: prompt compilation requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to compile prompt: ${error.message}`);
     }
@@ -1493,9 +1452,8 @@ class MCPPromptOptimizer {
       }
       return { content: [{ type: "text", text: output }] };
     } catch (error) {
-      const msg = error.message || '';
-      if (msg.includes('403') || msg.includes('TIER')) {
-        return { content: [{ type: "text", text: `Upgrade required: template versioning requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${msg}` }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Upgrade required: template versioning requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to list template versions: ${error.message}`);
     }
@@ -1509,9 +1467,8 @@ class MCPPromptOptimizer {
       const msg = result.message || `Template rolled back to version ${args.version_number}`;
       return { content: [{ type: "text", text: `# ✅ Rollback Complete\n\n${msg}\n\n**Template ID:** \`${args.template_id}\`\n**Version:** ${args.version_number}` }] };
     } catch (error) {
-      const msg = error.message || '';
-      if (msg.includes('403') || msg.includes('TIER')) {
-        return { content: [{ type: "text", text: `Upgrade required: template rollback requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${msg}` }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Upgrade required: template rollback requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to rollback template: ${error.message}`);
     }
@@ -1524,9 +1481,8 @@ class MCPPromptOptimizer {
       const msg = result.message || `Template ${args.template_id} published successfully`;
       return { content: [{ type: "text", text: `# ✅ Template Published\n\n${msg}\n\nThe template is now available for runtime delivery via \`get_prompt_by_slug\`.` }] };
     } catch (error) {
-      const msg = error.message || '';
-      if (msg.includes('403') || msg.includes('TIER')) {
-        return { content: [{ type: "text", text: `Upgrade required: template publishing requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${msg}` }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Upgrade required: template publishing requires Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to publish template: ${error.message}`);
     }
@@ -1556,9 +1512,8 @@ class MCPPromptOptimizer {
       }
       return { content: [{ type: "text", text: output }] };
     } catch (error) {
-      const msg = error.message || '';
-      if (msg.includes('403') || msg.includes('TIER')) {
-        return { content: [{ type: "text", text: `Upgrade required: evaluations require Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${msg}` }] };
+      if (error.statusCode === 403) {
+        return { content: [{ type: "text", text: `Upgrade required: evaluations require Pro tier or higher. Upgrade at /pricing.\n\nBackend error: ${error.message}` }] };
       }
       throw new Error(`Failed to run quick evaluation: ${error.message}`);
     }
@@ -1631,7 +1586,9 @@ class MCPPromptOptimizer {
               } catch {
                 errorMessage = `HTTP ${res.statusCode}: ${responseData}`;
               }
-              reject(new Error(errorMessage));
+              const httpError = new Error(errorMessage);
+              httpError.statusCode = res.statusCode;
+              reject(httpError);
             }
           } catch (parseError) {
             reject(new Error(`Invalid response format: ${parseError.message}`));
@@ -1787,7 +1744,7 @@ class MCPPromptOptimizer {
       output += `2. Generate your API key at https://promptoptimizer.xyz/dashboard\n`;
       output += `3. Run in your terminal:\n\n`;
       output += `\`\`\`\nnpx mcp-prompt-optimizer connect\n\`\`\`\n\n`;
-      output += `You get **7 LLM optimizations/month free**. Upgrade anytime for more.\n`;
+      output += `You get **20 LLM optimizations/month free**. Upgrade anytime for more.\n`;
     }
 
     return output;
@@ -1801,25 +1758,30 @@ class MCPPromptOptimizer {
       output += `**Usage:** 🟢 Unlimited\n`;
     } else {
       const used = quota.used || 0;
-      const limit = quota.limit || 5000;
+      const limit = quota.limit;
+
+      if (limit === undefined || limit === null) {
+        output += `**Usage:** ${used} used (limit unavailable — backend did not report a quota limit)\n`;
+      } else {
       const percentage = limit > 0 ? ((used / limit) * 100).toFixed(1) : 0;
-      
+
       let statusIcon = '🟢';
       if (percentage >= 90) statusIcon = '🔴';
       else if (percentage >= 75) statusIcon = '🟡';
-      
+
       output += `**Usage:** ${statusIcon} ${used}/${limit} (${percentage}%)\n`;
 
       const remaining = limit - used;
       if (remaining <= 0) {
         output += `\n❌ **Quota Exhausted** — You have no optimizations remaining this month.\n`;
-        output += `Upgrade at https://promptoptimizer.xyz/local-license\n`;
+        output += `Upgrade at https://promptoptimizer.xyz/pricing\n`;
         output += `*(Quota resets at the start of your next billing cycle)*\n`;
       } else if (percentage >= 90) {
-        output += `\n⚠️ **Critical** — ${remaining} optimization${remaining === 1 ? '' : 's'} remaining. Upgrade at https://promptoptimizer.xyz/local-license\n`;
+        output += `\n⚠️ **Critical** — ${remaining} optimization${remaining === 1 ? '' : 's'} remaining. Upgrade at https://promptoptimizer.xyz/pricing\n`;
       } else if (percentage >= 75) {
         output += `\n⚠️ **Warning** — Approaching your monthly limit.\n`;
       }
+      }
     }
 
     output += `\n## ✨ **Available Features**\n`;
@@ -1841,9 +1803,9 @@ class MCPPromptOptimizer {
     }
 
     output += `\n## 🔗 **Account Management**\n`;
-    output += `- Dashboard: https://promptoptimizer-blog.vercel.app/dashboard\n`;
-    output += `- Analytics: https://promptoptimizer-blog.vercel.app/analytics\n`;
-    output += `- Upgrade: https://promptoptimizer.xyz/local-license\n`;
+    output += `- Dashboard: https://promptoptimizer.xyz/dashboard\n`;
+    output += `- Analytics: https://promptoptimizer.xyz/analytics\n`;
+    output += `- Upgrade: https://promptoptimizer.xyz/pricing\n`;
 
     return output;
   }
@@ -1949,41 +1911,40 @@ class MCPPromptOptimizer {
     }
     
     output += `## 🔗 **Advanced Analytics**\n`;
-    output += `- Full Analytics: https://promptoptimizer-blog.vercel.app/analytics\n`;
-    output += `- Performance Dashboard: https://promptoptimizer-blog.vercel.app/dashboard\n`;
+    output += `- Full Analytics: https://promptoptimizer.xyz/analytics\n`;
+    output += `- Performance Dashboard: https://promptoptimizer.xyz/dashboard\n`;
     
     return output;
   }
 
   formatRealTimeStatus(status) {
     let output = `# ⚡ AG-UI Real-Time Status\n\n`;
-    
+    const metrics = status.metrics || {};
+
     output += `## 🚀 **Service Status**\n`;
-    output += `- **AG-UI Status:** ${status.agui_status === 'available' ? '🟢 Available' : '🔴 Unavailable'}\n`;
-    output += `- **Streaming Optimization:** ${status.streaming_optimization ? '✅ Enabled' : '❌ Disabled'}\n`;
-    output += `- **WebSocket Support:** ${status.websocket_support ? '✅ Enabled' : '❌ Disabled'}\n`;
-    output += `- **Real-time Analytics:** ${status.real_time_analytics ? '✅ Enabled' : '❌ Disabled'}\n\n`;
-    
-    if (status.active_optimizations !== undefined) {
-      output += `## 📈 **Current Activity**\n`;
-      output += `- **Active Optimizations:** ${status.active_optimizations}\n`;
-      output += `- **Average Response Time:** ${status.average_response_time}\n\n`;
+    output += `- **AG-UI Status:** ${status.status === 'healthy' ? '🟢 Healthy' : '🔴 Degraded'}\n\n`;
+
+    output += `## 📈 **Current Activity**\n`;
+    output += `- **Active Sessions:** ${metrics.active_sessions ?? 'unknown'}\n`;
+    output += `- **Total Connections:** ${metrics.total_connections ?? 'unknown'}\n`;
+    output += `- **Total Optimizations:** ${metrics.total_optimizations ?? 'unknown'}\n`;
+    if (metrics.uptime_seconds !== undefined) {
+      output += `- **Uptime:** ${Math.round(metrics.uptime_seconds)}s\n`;
     }
-    
-    if (status.features) {
-      const features = status.features;
+    output += `\n`;
+
+    if (metrics.features_enabled) {
       output += `## ⚡ **Available Features**\n`;
-      if (features.live_optimization) output += `✅ Live Optimization\n`;
-      if (features.collaborative_editing) output += `✅ Collaborative Editing\n`;
-      if (features.instant_feedback) output += `✅ Instant Feedback\n`;
-      if (features.performance_monitoring) output += `✅ Performance Monitoring\n`;
+      for (const [feature, enabled] of Object.entries(metrics.features_enabled)) {
+        if (enabled) output += `✅ ${feature}\n`;
+      }
       output += `\n`;
     }
-    
+
     output += `## 🔗 **Real-Time Access**\n`;
-    output += `- Live Dashboard: https://promptoptimizer-blog.vercel.app/live\n`;
+    output += `- Live Dashboard: https://promptoptimizer.xyz/live\n`;
     output += `- WebSocket Endpoint: Available via API\n`;
-    
+
     return output;
   }
 
@@ -2001,7 +1962,7 @@ async function startValidatedMCPServer() {
   try {
     const apiKey = process.env.OPTIMIZER_API_KEY;
     if (!apiKey) {
-      console.error('❌ API key required. Get one at https://promptoptimizer.xyz/local-license');
+      console.error('❌ API key required. Get one free at https://promptoptimizer.xyz/dashboard');
       process.exit(1);
     }
     
@@ -2179,7 +2140,7 @@ async function runConnectWizard() {
     }
     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('   Free plan: 20 LLM optimizations/month.');
       console.log('   Upgrade at https://promptoptimizer.xyz/pricing\n');
     }
   }
@@ -2198,12 +2159,50 @@ async function runConnectWizard() {
   });
 }
 
+function printCliHelp() {
+  console.log(`MCP Prompt Optimizer v${packageJson.version}
+
+Usage:
+  mcp-prompt-optimizer                    Start the MCP server (used by MCP clients)
+  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 diagnose           Run comprehensive diagnostic
+  mcp-prompt-optimizer clear-cache        Clear validation cache
+  mcp-prompt-optimizer help               Show this help
+  mcp-prompt-optimizer version            Show version information`);
+}
+
+function printCliVersion() {
+  console.log(packageJson.version);
+}
+
+const CLI_COMMANDS = {
+  connect: runConnectWizard,
+  'check-status': () => require('./lib/check-status')().then(() => process.exit(0)),
+  'validate-key': () => require('./lib/validate-key')().then(() => process.exit(0)),
+  'clear-cache': () => require('./lib/clear-cache')().then(() => process.exit(0)),
+  diagnose: () => require('./lib/diagnose')().then(() => process.exit(0)),
+  help: printCliHelp,
+  '--help': printCliHelp,
+  '-h': printCliHelp,
+  version: printCliVersion,
+  '--version': printCliVersion,
+  '-v': printCliVersion,
+};
+
 if (require.main === module) {
   const args = process.argv.slice(2);
-  if (args[0] === 'connect') {
-    runConnectWizard();
-  } else {
+  const cmd = args[0];
+
+  if (!cmd) {
     startValidatedMCPServer();
+  } else if (CLI_COMMANDS[cmd]) {
+    CLI_COMMANDS[cmd]();
+  } else {
+    console.error(`❌ Unknown command: ${cmd}\n`);
+    printCliHelp();
+    process.exit(1);
   }
 }
 

package/lib/api-key-manager.js

@@ -241,7 +241,11 @@ class CloudApiKeyManager {
             // SECURITY: Offline mode removed - backend validation required
             // No cache fallback beyond 2 hours
 
-            throw new Error(`API key validation failed: ${error.message}. Please check your internet connection.`);
+            // A 4xx means the backend rejected the key itself, not a connectivity
+            // problem — telling the user to check their internet is wrong there.
+            const isClientError = error.statusCode >= 400 && error.statusCode < 500;
+            const hint = isClientError ? '' : ' Please check your internet connection.';
+            throw new Error(`API key validation failed: ${error.message}.${hint}`);
         }
     }
 
@@ -268,7 +272,17 @@ class CloudApiKeyManager {
             } catch (error) {
                 lastError = error;
                 this.log(`Attempt ${attempt} failed: ${error.message}`, 'warn');
-                
+
+                // A 4xx means the backend definitively rejected the request (bad/expired
+                // key, malformed request) — retrying with the same key can't change that.
+                // Only network errors and 5xx (transient/server-side) are worth retrying.
+                // 429 is the exception: rate limits are exactly what backoff is for.
+                const isClientError = error.statusCode >= 400 && error.statusCode < 500 && error.statusCode !== 429;
+                if (isClientError) {
+                    this.log('Non-retryable client error — not retrying', 'error');
+                    break;
+                }
+
                 if (attempt < this.maxRetries) {
                     const delay = this.calculateRetryDelay(attempt);
                     this.log(`Retrying in ${delay}ms...`);
@@ -579,7 +593,7 @@ class CloudApiKeyManager {
 
         throw new Error(
             'API key required. Set the OPTIMIZER_API_KEY environment variable.\n' +
-            'Get your API key at: https://promptoptimizer.xyz/local-license'
+            'Get your API key at: https://promptoptimizer.xyz/dashboard'
         );
     }
 
@@ -690,7 +704,9 @@ class CloudApiKeyManager {
                             } catch {
                                 errorMessage = `HTTP ${res.statusCode}: ${responseData}`;
                             }
-                            reject(new Error(errorMessage));
+                            const httpError = new Error(errorMessage);
+                            httpError.statusCode = res.statusCode;
+                            reject(httpError);
                         }
                     } catch (parseError) {
                         reject(new Error(`Invalid response format: ${parseError.message}`));

package/lib/check-status.js

@@ -10,7 +10,7 @@ async function checkStatus() {
         if (!apiKey) {
             console.error('❌ No API key found');
             console.log('\n📝 Set your API key to check status:');
-            console.log('   export OPTIMIZER_API_KEY=sk-local-your-key-here'); // Aligned with free tier/development
+            console.log('   export OPTIMIZER_API_KEY=sk-opt-your-key-here');
             if (developmentMode) {
                 console.log('\n🧪 Development Mode Options:');
                 console.log('   export OPTIMIZER_API_KEY=sk-dev-test-key');
@@ -25,7 +25,13 @@ async function checkStatus() {
         console.log('='.repeat(50));
         console.log(`🎯 Subscription Tier: ${apiKeyInfo.tier}`);
         console.log(`🔑 API Key Type: ${apiKeyInfo.keyType}`);
-        console.log(`✅ Key Status: ${apiKeyInfo.isValid ? 'Valid' : 'Invalid'}`);
+        console.log(`${apiKeyInfo.isValid ? '✅' : '❌'} Key Status: ${apiKeyInfo.isValid ? 'Valid' : 'Invalid'}`);
+        if (!apiKeyInfo.isValid) {
+            // getApiKeyInfo() reports failure via isValid:false rather than throwing,
+            // so this catch block never sees it — exit(1) has to happen here instead.
+            if (apiKeyInfo.error) console.log(`   ${apiKeyInfo.error}`);
+            process.exit(1);
+        }
     } catch (error) {
         console.error(`❌ Status check failed: ${error.message}\n`);
         process.exit(1);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-prompt-optimizer",
-  "version": "3.7.3",
+  "version": "3.7.5",
   "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": {
@@ -124,8 +124,8 @@
     "required_keys": [
       {
         "name": "OPTIMIZER_API_KEY",
-        "format": "sk-opt-*, sk-team-*, sk-dev-*, or sk-local-*",
-        "description": "Cloud API key from promptoptimizer.xyz/local-license or development key for testing",
+        "format": "sk-opt-*, sk-team-*, or sk-dev-*",
+        "description": "Cloud API key from promptoptimizer.xyz/dashboard or development key for testing",
         "required": true
       }
     ],
@@ -195,6 +195,28 @@
     "last_sync": "2026-06-01T00:00:00Z"
   },
   "release_notes": {
+    "v3.7.5": {
+      "major_features": [
+        "Fixed: 10 MCP tools (generate_agent_sop, transform_for_framework, generate_harness_bundle, explore_sop_approaches, get_prompt_by_slug, compile_prompt, list_template_versions, rollback_template, publish_template, run_quick_evaluation) called backend routes that only accepted a JWT, which this stdio client can never obtain — every call failed unconditionally. Backend now accepts API-key auth on these routes too.",
+        "Fixed: the tier-upgrade message for these tools never fired because the code checked for the literal string '403' inside the error body, which never appears there (that's the HTTP status code, not body text). Now checks the real status code.",
+        "Fixed: get_optimization_insights and get_real_time_status fell back to hardcoded fake data (fabricated optimization counts, fake AG-UI metrics) on any backend error, presented as real account data. Both now report unavailability honestly instead.",
+        "Fixed: formatRealTimeStatus was never reading the AG-UI status endpoint's actual response shape, even on success.",
+        "Fixed: formatQuotaStatus invented a fake 5000 quota limit when the backend didn't report one.",
+        "Fixed: free-tier quota text said 7/month; actual limit is 20.",
+        "Fixed: dead promptoptimizer-blog.vercel.app domain and wrong sk-local-* key-format claims (that's the sibling local package's prefix, not this one's) across index.js, check-status.js, and package.json."
+      ],
+      "breaking_changes": [],
+      "migration_guide": "No migration required. Users who called any of the 10 previously-broken MCP tools will now get real results instead of an auth error."
+    },
+    "v3.7.4": {
+      "major_features": [
+        "Fixed: 6 of 8 documented CLI commands (check-status, validate-key, diagnose, clear-cache, help, version) were not implemented in the argv dispatcher and silently started the blocking MCP server instead, hanging the terminal. Now wired to their lib/*.js implementations.",
+        "Fixed: unrecognized CLI arguments now print an error + usage to stderr and exit(1), instead of silently falling through to server startup. Removes the entire hung-terminal bug class, not just the known commands.",
+        "Removed 'test' from documented CLI commands: it mapped to a maintainer-only pre-publish script (tests/test-runner.js) that isn't included in the published package."
+      ],
+      "breaking_changes": [],
+      "migration_guide": "No migration required. Only affects users who ran documented CLI subcommands other than 'connect', which previously hung."
+    },
     "v3.7.3": {
       "major_features": [
         "Docs only: corrected stale free-tier quota in README (7 optimizations/month -> 20), matching the backend enforcement fix"