mcp-prompt-optimizer 3.0.5 → 3.1.1

package/CHANGELOG.md

@@ -5,6 +5,12 @@ 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).
 
+## [3.1.1] - 2026-04-10
+
+### Changed
+- 💰 **Pricing Alignment**: Updated README to reflect current subscription tiers and optimization quotas.
+- 📦 **Version Bump**: Incremented version to v3.1.1 to resolve npm publishing conflict with existing v3.1.0 on the registry.
+
 ## [3.0.1] - 2025-12-09
 
 ### Fixed

package/README.md

@@ -1,6 +1,7 @@
-# MCP Prompt Optimizer v3.0.3
+# MCP Prompt Optimizer v3.1.1
+
+🚀 **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 $2.99/month.
 
 ## ✨ Key Features
 
@@ -120,7 +121,7 @@ To address this effectively:
 
 ## 🧠 AI Context Detection
 
-The server automatically detects your prompt type and routes it to the appropriate optimization template. You can also specify `ai_context` manually in the tool call.
+The server automatically detects your prompt type and routes it to the appropriate optimization template.
 
 | Context | `ai_context` value | Example patterns |
 |---|---|---|
@@ -133,6 +134,11 @@ The server automatically detects your prompt type and routes it to the appropria
 | Creative writing | `creative_writing` | `story`, `poem`, `script`, `blog`, `copywriting` |
 | Email & communication | `human_communication` | `email`, `letter`, `memo`, `formal`, `reply` |
 | Image generation | `image_generation` | `photorealistic`, `midjourney`, `dall-e`, `portrait` |
+| Business & Strategy | `business_strategy` | `market analysis`, `swot`, `business plan` |
+| Technical Strategy | `technical_strategy` | `architecture`, `system design`, `migration plan` |
+| Legal & Compliance | `legal_compliance` | `contract`, `gdpr`, `terms of service`, `audit` |
+| Medical & Health | `medical_healthcare` | `clinical`, `diagnosis`, `treatment`, `hipaa` |
+| Education | `educational_content` | `lesson plan`, `syllabus`, `curriculum`, `quiz` |
 | General | `general_assistant` | Everything else |
 
 ### Image Generation
@@ -232,6 +238,47 @@ 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.
+
+### `generate_agent_sop`
+Generate a structured SOP document for an AI agent from a goal description. Returns markdown SOP ready for use.
+```json
+{
+  "goal": "What the agent should accomplish",
+  "context": "Additional context, constraints, or domain info (optional)",
+  "model_id": "Model to use (optional)"
+}
+```
+
+### `generate_skill_package`
+Generate a complete skill package (SOP + SKILL.md + reference + examples + helper.py) for a given agent goal. Takes 30–90 seconds (async with polling).
+```json
+{
+  "goal": "What the agent should accomplish",
+  "format": "knowledge_doc",
+  "model_id": "Model to use (optional)"
+}
+```
+`format` is one of `knowledge_doc` (default) or `agent_spec`.
+
+### `transform_for_framework`
+Transform a SOP into native code for your agent framework: LangChain tool, AutoGen agent, or Claude Code skill.
+```json
+{
+  "sop_content": "The SOP markdown content",
+  "goal": "What the agent should accomplish",
+  "framework": "langchain_tool"
+}
+```
+`framework` is one of `langchain_tool`, `autogen_agent`, or `claude_skill`.
+
+### `get_ce_quota_status`
+Check your Context Engineer credit balance and what workflows are available at your tier. No parameters required.
+
+---
+
 ## 🎛️ Advanced Model Configuration (Optional)
 
 Configure custom models in the WebUI and the MCP server uses them automatically.
@@ -267,11 +314,11 @@ Configure custom models in the WebUI and the MCP server uses them automatically.
 
 ## 💰 Subscription Plans
 
-| Plan | Price | Optimizations/month | Team members |
-|---|---|---|---|
-| 🎯 Explorer | $2.99/mo | 5,000 | 1 |
-| 🎨 Creator | $25.99/mo | 18,000 | 2 + 3 keys |
-| 🚀 Innovator | $69.99/mo | 75,000 | 5 + 10 keys |
+| Plan | Price | Optimizations/month | CE Credits | Team members |
+|---|---|---|---|---|
+| 🎯 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.
 

package/index.js

@@ -5,7 +5,7 @@
  * Production-grade with Bayesian optimization, AG-UI real-time features, enhanced network resilience, 
  * development mode, and complete backend alignment
  * 
- * Version: 3.0.2 - Aligned with FastAPI Backend production-v2.2.0-stable
+ * Version: 3.1.0 - CE tools: generate_agent_sop, generate_skill_package, transform_for_framework, get_ce_quota_status
  */
 
 const { Server } = require('@modelcontextprotocol/sdk/server/index.js');
@@ -53,6 +53,15 @@ const ENDPOINTS = {
 
   /** AG‑UI status (GET) */
   AGUI_STATUS:         '/api/status',
+
+  /** Context Engineer (CE) endpoints */
+  CE: {
+    SOP:                     '/api/v1/context-engineer/sop',
+    GENERATE_SKILL_PACKAGE:  '/api/v1/context-engineer/generate-skill-package',
+    SESSION:                 (id) => `/api/v1/context-engineer/sessions/${id}`,
+    TRANSFORM:               '/api/v1/context-engineer/transform',
+    QUOTA:                   '/api/v1/context-engineer/quota',
+  },
 };
 
 class MCPPromptOptimizer {
@@ -105,7 +114,9 @@ class MCPPromptOptimizer {
                 type: "string",
                 enum: [
                   "human_communication", "llm_interaction", "image_generation", "technical_automation",
-                  "structured_output", "code_generation", "api_automation"
+                  "structured_output", "code_generation", "api_automation", "data_analysis",
+                  "creative_writing", "business_strategy", "technical_strategy", "academic_research",
+                  "legal_compliance", "medical_healthcare", "educational_content"
                 ],
                 description: "The context for the AI's task (auto-detected if not specified with enhanced detection)"
               },
@@ -259,6 +270,50 @@ class MCPPromptOptimizer {
             required: ["prompt"]
           }
         },
+        {
+          name: "generate_agent_sop",
+          description: "Generate a structured SOP document for an AI agent from a goal description.",
+          inputSchema: {
+            type: "object",
+            properties: {
+              goal: { type: "string", description: "What the agent should accomplish" },
+              context: { type: "string", description: "Additional context (optional)" },
+              model_id: { type: "string", description: "Model to use (optional)" }
+            },
+            required: ["goal"]
+          }
+        },
+        {
+          name: "generate_skill_package",
+          description: "Generate a complete skill package (SOP + SKILL.md + examples + helper.py) for an AI agent. Takes 30-120 seconds (async).",
+          inputSchema: {
+            type: "object",
+            properties: {
+              goal: { type: "string", description: "What the agent should accomplish" },
+              format: { type: "string", enum: ["knowledge_doc", "agent_spec"], description: "Output format" },
+              model_id: { type: "string", description: "Model to use (optional)" }
+            },
+            required: ["goal"]
+          }
+        },
+        {
+          name: "transform_for_framework",
+          description: "Transform a SOP into native code for LangChain, AutoGen, or Claude Code.",
+          inputSchema: {
+            type: "object",
+            properties: {
+              sop_content: { type: "string", description: "SOP content to transform" },
+              goal: { type: "string", description: "What the agent should accomplish" },
+              framework: { type: "string", enum: ["langchain_tool", "autogen_agent", "claude_skill"], description: "Target framework" }
+            },
+            required: ["sop_content", "goal", "framework"]
+          }
+        },
+        {
+          name: "get_ce_quota_status",
+          description: "Check your Context Engineer credit balance and available workflow types.",
+          inputSchema: { type: "object", properties: {}, additionalProperties: false }
+        },
       ];
 
       // Add advanced tools if Bayesian optimization is enabled
@@ -311,6 +366,10 @@ class MCPPromptOptimizer {
           case "update_template": return await this.handleUpdateTemplate(args);
           case "get_optimization_insights": return await this.handleGetOptimizationInsights(args);
           case "get_real_time_status": return await this.handleGetRealTimeStatus();
+          case "generate_agent_sop": return await this.handleGenerateAgentSop(args);
+          case "generate_skill_package": return await this.handleGenerateSkillPackage(args);
+          case "transform_for_framework": return await this.handleTransformForFramework(args);
+          case "get_ce_quota_status": return await this.handleGetCEQuotaStatus();
           default: throw new Error(`Unknown tool: ${name}`);
         }
       } catch (error) {
@@ -899,7 +958,7 @@ class MCPPromptOptimizer {
       const { template_id, ...updateData } = args;
       // Filter out undefined values so we only send fields that are being updated
       Object.keys(updateData).forEach(key => updateData[key] === undefined && delete updateData[key]);
-      
+
       const result = await this.callBackendAPI(ENDPOINTS.TEMPLATE.UPDATE(template_id), updateData, 'PATCH'); // PATCH is better for partial updates
       let output = `# ✅ Template Updated Successfully!\n\n`;
       output += `**ID:** \`${result.id}\`\n`;
@@ -911,7 +970,103 @@ class MCPPromptOptimizer {
     }
   }
 
-  async _buildUrl(path) {
+  async handleGenerateAgentSop(args) {
+    if (!args.goal) throw new Error('goal is required');
+    const payload = { goal: args.goal };
+    if (args.context) payload.context = args.context;
+    if (args.model_id) payload.model_id = args.model_id;
+    try {
+      const result = await this.callBackendAPI(ENDPOINTS.CE.SOP, payload);
+      const sopContent = result.sop || result.content || result.result || JSON.stringify(result, null, 2);
+      return { content: [{ type: "text", text: `# Agent SOP Generated\n\n${sopContent}\n\n---\n*Generated by MCP Prompt Optimizer CE*` }] };
+    } catch (error) {
+      throw new Error(`Failed to generate SOP: ${error.message}`);
+    }
+  }
+
+  async handleGenerateSkillPackage(args) {
+    if (!args.goal) throw new Error('goal is required');
+    const payload = { goal: args.goal, format: args.format || 'knowledge_doc' };
+    if (args.model_id) payload.model_id = args.model_id;
+    let workflowError = null;
+    try {
+      const startResult = await this.callBackendAPI(ENDPOINTS.CE.GENERATE_SKILL_PACKAGE, payload);
+      const sessionId = startResult.session_id;
+      if (!sessionId) {
+        return { content: [{ type: "text", text: this._formatSkillPackage(startResult) }] };
+      }
+      for (let i = 0; i < 24; i++) {
+        await new Promise(resolve => setTimeout(resolve, 5000));
+        const status = await this.callBackendAPI(ENDPOINTS.CE.SESSION(sessionId), null, 'GET');
+        const state = status.workflow_state || status.current_state;
+        if (state === 'complete') return { content: [{ type: "text", text: this._formatSkillPackage(status) }] };
+        if (state === 'failed') {
+          workflowError = new Error(`Generation failed: ${status.error || 'Unknown error'}`);
+          throw workflowError;
+        }
+      }
+      workflowError = new Error(`Timed out after 120s. Session ID: ${sessionId}`);
+      throw workflowError;
+    } catch (error) {
+      if (error === workflowError) throw error;
+      throw new Error(`Failed to generate skill package: ${error.message}`);
+    }
+  }
+
+  async handleTransformForFramework(args) {
+    if (!args.sop_content) throw new Error('sop_content is required');
+    if (!args.goal) throw new Error('goal is required');
+    if (!args.framework) throw new Error('framework is required');
+    const valid = ['langchain_tool', 'autogen_agent', 'claude_skill'];
+    if (!valid.includes(args.framework)) throw new Error(`framework must be one of: ${valid.join(', ')}`);
+    try {
+      const result = await this.callBackendAPI(ENDPOINTS.CE.TRANSFORM, {
+        sop_content: args.sop_content, goal: args.goal, framework: args.framework
+      });
+      const code = result.code || result.content || result.result || JSON.stringify(result, null, 2);
+      return { content: [{ type: "text", text: `# ${args.framework} Implementation\n\n\`\`\`python\n${code}\n\`\`\`\n\n---\n*Transformed by MCP Prompt Optimizer CE*` }] };
+    } catch (error) {
+      throw new Error(`Failed to transform: ${error.message}`);
+    }
+  }
+
+  async handleGetCEQuotaStatus() {
+    try {
+      const result = await this.callBackendAPI(ENDPOINTS.CE.QUOTA, null, 'GET');
+      const lines = ['## CE Credit Balance', ''];
+      if (result.is_unlimited) {
+        lines.push(`Credits: **Unlimited** (${result.credits_used || 0} used this period)`);
+      } else {
+        lines.push(`Credits: **${result.credits_remaining ?? 'N/A'}** of ${result.credits_limit} remaining (${result.credits_used || 0} used)`);
+      }
+      lines.push('', '## Available Workflows');
+      if (result.workflow_availability) {
+        for (const [type, info] of Object.entries(result.workflow_availability)) {
+          lines.push(`- ${info.available ? '✓' : '✗'} ${type}: ${info.cost_credits} credit(s)`);
+        }
+      }
+      if (result.message) lines.push('', result.message);
+      return { content: [{ type: "text", text: lines.join('\n') }] };
+    } catch (error) {
+      throw new Error(`Failed to get CE quota: ${error.message}`);
+    }
+  }
+
+  _formatSkillPackage(result) {
+    const sections = ['# Skill Package Generated'];
+    const artifacts = result.artifacts || result.steps || {};
+    if (typeof artifacts === 'object' && Object.keys(artifacts).length > 0) {
+      for (const [key, value] of Object.entries(artifacts)) {
+        if (value && typeof value === 'string') sections.push(`\n## ${key}\n\n${value}`);
+      }
+    } else {
+      sections.push('\n```json\n' + JSON.stringify(result, null, 2) + '\n```');
+    }
+    sections.push('\n---\n*Generated by MCP Prompt Optimizer CE*');
+    return sections.join('\n');
+  }
+
+  _buildUrl(path) {
     return `${this.backendUrl}${path}`;
   }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-prompt-optimizer",
-  "version": "3.0.5",
+  "version": "3.1.1",
   "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": {