@vibetasks/mcp-server 0.1.0 → 0.2.1

package/README.md

@@ -1,10 +1,14 @@
-# TaskFlow MCP Server
+# VibeTasks MCP Server
 
-Model Context Protocol (MCP) server for TaskFlow integration with Claude Code, Cursor, and other AI coding tools.
+Model Context Protocol (MCP) server for VibeTasks integration with Claude Code, Cursor, and other AI coding tools.
 
 ## Features
 
-- **8 MCP Tools** for full task management (create, read, update, delete, search, complete, batch create with subtasks, log sessions)
+- **11 MCP Tools** for full task management (create, read, update, delete, search, complete, vibing status, context notes, batch create with subtasks, log sessions)
+- **Status Workflow**: `todo` -> `vibing` -> `done` - track what you're actively working on
+- **Context Notes**: "Where I left off" notes to capture your progress and next steps
+- **Project Auto-Detection**: Automatically tags tasks with project name from git repository
+- **WIP Limit Awareness**: Warns when you have too many tasks in "vibing" status
 - **3 MCP Resources** for context-aware AI (active tasks, today's tasks, upcoming tasks)
 - **Claude Code Hooks** for automatic session logging
 - **TodoWrite Integration** for automatic task syncing from Claude's todo lists
@@ -22,43 +26,74 @@ Model Context Protocol (MCP) server for TaskFlow integration with Claude Code, C
 ### Quick Install
 
 ```bash
-# From the apps/mcp-server directory
-npm install
-npm run build
-bash scripts/install.sh
+# Install globally from npm
+npm install -g @vibetasks/mcp-server
+
+# Verify installation
+vibetasks-mcp --version
 ```
 
-The installation script will:
-1. Build the MCP server
-2. Create Claude Code configuration
-3. Set up hooks for automatic session logging
+### Configure Claude Code
 
-### Manual Installation
+Edit your Claude Code config file:
+- **macOS/Linux**: `~/.config/claude-code/config.json`
+- **Windows**: `%APPDATA%\claude-code\config.json`
+
+```json
+{
+  "mcpServers": {
+    "vibetasks": {
+      "command": "vibetasks-mcp",
+      "env": {
+        "TASKFLOW_SUPABASE_URL": "https://your-project.supabase.co",
+        "TASKFLOW_SUPABASE_KEY": "your-supabase-anon-key"
+      }
+    }
+  }
+}
+```
+
+**Restart Claude Code** after updating the config.
+
+### Manual Installation (Development)
+
+If you're developing locally instead of using the npm package:
 
-1. **Build the server:**
 ```bash
+# From the apps/mcp-server directory
+npm install
 npm run build
 ```
 
-2. **Get your Supabase anon key:**
-   - Go to https://supabase.com/dashboard/project/_/settings/api
-   - Copy the `anon` public key
+Then configure Claude Code with the full path:
+
+```json
+{
+  "mcpServers": {
+    "vibetasks": {
+      "command": "node",
+      "args": ["/absolute/path/to/taskflow/apps/mcp-server/dist/index.js"],
+      "env": {
+        "TASKFLOW_SUPABASE_URL": "https://your-project.supabase.co",
+        "TASKFLOW_SUPABASE_KEY": "your-supabase-anon-key"
+      }
+    }
+  }
+}
+```
 
-3. **Configure Claude Code:**
+### Optional: Session Hooks
 
-Edit `~/.config/claude-code/config.json`:
+For automatic session logging (creates completed tasks when you end AI sessions):
 
 ```json
 {
   "mcpServers": {
-    "taskflow": {
-      "command": "node",
-      "args": [
-        "/absolute/path/to/taskflow/apps/mcp-server/dist/index.js"
-      ],
+    "vibetasks": {
+      "command": "vibetasks-mcp",
       "env": {
-        "TASKFLOW_SUPABASE_URL": "https://cbkkztbcoitrfcleghfd.supabase.co",
-        "TASKFLOW_SUPABASE_KEY": "your_anon_key_here"
+        "TASKFLOW_SUPABASE_URL": "...",
+        "TASKFLOW_SUPABASE_KEY": "..."
       }
     }
   },
@@ -66,22 +101,20 @@ Edit `~/.config/claude-code/config.json`:
     "SessionStart": [
       {
         "type": "command",
-        "command": "node",
-        "args": ["/absolute/path/to/dist/index.js"],
+        "command": "vibetasks-mcp",
         "env": {
           "CLAUDE_HOOK_TYPE": "SessionStart",
-          "TASKFLOW_SUPABASE_URL": "https://cbkkztbcoitrfcleghfd.supabase.co"
+          "TASKFLOW_SUPABASE_URL": "..."
         }
       }
     ],
     "Stop": [
       {
         "type": "command",
-        "command": "node",
-        "args": ["/absolute/path/to/dist/index.js"],
+        "command": "vibetasks-mcp",
         "env": {
           "CLAUDE_HOOK_TYPE": "SessionEnd",
-          "TASKFLOW_SUPABASE_URL": "https://cbkkztbcoitrfcleghfd.supabase.co"
+          "TASKFLOW_SUPABASE_URL": "..."
         }
       }
     ]
@@ -89,8 +122,6 @@ Edit `~/.config/claude-code/config.json`:
 }
 ```
 
-4. **Restart Claude Code**
-
 ## Usage
 
 ### MCP Tools
@@ -100,7 +131,7 @@ Access tools by typing `@` in Claude Code:
 #### create_task
 Create a new task:
 ```
-@taskflow create_task
+@vibetasks create_task
   title: "Add authentication"
   notes: "Implement OAuth with Supabase"
   priority: "high"
@@ -108,58 +139,93 @@ Create a new task:
   tags: ["backend", "security"]
 ```
 
-#### get_tasks
-Get filtered tasks:
+#### create_task_with_subtasks
+Create a parent task with subtasks in one call (perfect for TodoWrite integration):
 ```
-@taskflow get_tasks filter: "today"
+@vibetasks create_task_with_subtasks
+  title: "Implement user authentication"
+  subtasks: ["Create login form", "Add API endpoints", "Implement JWT handling"]
+  priority: "high"
+  due_date: "2026-01-15"
+  tags: ["backend", "auth"]
 ```
 
-Filters: `all`, `today`, `upcoming`, `completed`
+**Use case:** When using Claude's TodoWrite feature, automatically mirror your todo list to VibeTasks for persistent tracking beyond the session.
 
-#### complete_task
-Mark a task complete:
+#### list_tasks
+Get tasks with optional status filter:
 ```
-@taskflow complete_task task_id: "abc-123..."
+@vibetasks list_tasks status: "todo"
+@vibetasks list_tasks status: "vibing"
+@vibetasks list_tasks status: "done"
 ```
 
+Status filters:
+- `todo` - Tasks not yet started
+- `vibing` - Tasks currently in progress
+- `done` - Completed tasks
+- (no filter) - All tasks
+
 #### update_task
-Update task properties:
+Update task properties including status:
 ```
-@taskflow update_task
+@vibetasks update_task
   task_id: "abc-123..."
   title: "Updated title"
   priority: "medium"
+  status: "vibing"
 ```
 
-#### delete_task
-Delete a task:
+#### complete_task
+Mark a task as done:
 ```
-@taskflow delete_task task_id: "abc-123..."
+@vibetasks complete_task task_id: "abc-123..."
 ```
 
-#### search_tasks
-Search by title:
+#### start_vibing
+Mark a task as "vibing" (in progress). This sets the status to `vibing` and optionally adds context notes:
 ```
-@taskflow search_tasks query: "authentication" limit: 10
+@vibetasks start_vibing
+  task_id: "abc-123..."
+  context_notes: "Working on the login form, need to add validation next"
 ```
 
-#### create_task_with_subtasks
-Create a parent task with subtasks in one call (perfect for TodoWrite integration):
+**WIP Limit Awareness**: If you have 3+ tasks already in "vibing" status, the tool will warn you to finish existing work before starting new tasks.
+
+#### get_vibing_tasks
+Get all tasks currently in "vibing" (in progress) status:
 ```
-@taskflow create_task_with_subtasks
-  title: "Implement user authentication"
-  subtasks: ["Create login form", "Add API endpoints", "Implement JWT handling"]
-  priority: "high"
-  due_date: "2026-01-15"
-  tags: ["backend", "auth"]
+@vibetasks get_vibing_tasks
 ```
 
-**Use case:** When using Claude's TodoWrite feature, automatically mirror your todo list to TaskFlow for persistent tracking beyond the session.
+Returns tasks you're actively working on, along with their context notes showing where you left off.
+
+#### set_context_notes
+Update the "where I left off" notes for a task:
+```
+@vibetasks set_context_notes
+  task_id: "abc-123..."
+  context_notes: "Finished the API, need to wire up the frontend next"
+```
+
+Use this to capture your progress before switching tasks or ending a session.
+
+#### delete_task
+Delete a task:
+```
+@vibetasks delete_task task_id: "abc-123..."
+```
+
+#### search_tasks
+Search by title:
+```
+@vibetasks search_tasks query: "authentication" limit: 10
+```
 
 #### log_ai_session
 Manually log a session:
 ```
-@taskflow log_ai_session
+@vibetasks log_ai_session
   summary: "Implemented user authentication"
   files: ["auth.ts", "login.tsx"]
   duration_minutes: 45
@@ -169,12 +235,54 @@ Manually log a session:
 
 Resources provide automatic context to AI:
 
-- `taskflow://tasks/active` - All incomplete tasks
-- `taskflow://tasks/today` - Tasks due today
-- `taskflow://tasks/upcoming` - Future tasks
+- `vibetasks://tasks/active` - All incomplete tasks
+- `vibetasks://tasks/today` - Tasks due today
+- `vibetasks://tasks/upcoming` - Future tasks
+- `vibetasks://tasks/vibing` - Tasks currently in progress (with context notes)
 
 The AI can access these without explicit tool calls.
 
+### Status Workflow
+
+VibeTasks uses a simple 3-state workflow:
+
+```
+todo -> vibing -> done
+```
+
+- **todo**: Task is captured but not started
+- **vibing**: You're actively working on this task (WIP)
+- **done**: Task is complete
+
+**Why "vibing"?** It's a playful term for "work in progress" that fits the vibe coding culture. When you're vibing on a task, you're in the zone.
+
+### Context Notes ("Where I Left Off")
+
+Each task can have context notes that capture your progress:
+
+```
+@vibetasks set_context_notes
+  task_id: "abc-123..."
+  context_notes: "Finished auth API, need to add frontend form. Check auth.ts for the endpoint structure."
+```
+
+Context notes are shown when you:
+- Call `get_vibing_tasks` - see where you left off on all active work
+- Start a new session - AI sees your current context
+- Switch between tasks - never lose your place
+
+### Project Auto-Detection
+
+When you create tasks, VibeTasks automatically detects your current project from git:
+
+```bash
+# In a git repo with remote "github.com/user/my-project"
+@vibetasks create_task title: "Fix bug"
+# Task is auto-tagged with "my-project"
+```
+
+This helps filter tasks by project when you have multiple codebases.
+
 ### Automatic Session Logging
 
 When Claude Code hooks are configured:
@@ -250,28 +358,30 @@ CLAUDE_HOOK_TYPE=SessionEnd node dist/index.js
 
 ### Server Not Appearing in Claude Code
 
-1. Check config file: `~/.config/claude-code/config.json`
-2. Verify dist/index.js exists: `ls apps/mcp-server/dist/`
+1. Check config file location:
+   - macOS/Linux: `~/.config/claude-code/config.json`
+   - Windows: `%APPDATA%\claude-code\config.json`
+2. Verify `vibetasks-mcp` is installed: `vibetasks-mcp --version`
 3. Check logs: Restart Claude Code with verbose logging
-4. Verify authentication: `taskflow config`
+4. Verify authentication: `vibetasks config`
 
 ### Authentication Errors
 
 ```bash
-# Re-login to TaskFlow
-taskflow login
+# Re-login to VibeTasks
+vibetasks login
 
 # Verify tokens are stored
-taskflow config
+vibetasks config
 ```
 
 ### Hooks Not Working
 
 1. Check hook configuration in `config.json`
-2. Verify file paths are absolute
+2. Verify environment variables are set correctly
 3. Test hooks manually:
 ```bash
-CLAUDE_HOOK_TYPE=SessionStart node dist/index.js
+CLAUDE_HOOK_TYPE=SessionStart vibetasks-mcp
 ```
 
 ## Architecture
@@ -284,15 +394,16 @@ CLAUDE_HOOK_TYPE=SessionStart node dist/index.js
          │ STDIO
          │
 ┌────────▼────────┐
-│   MCP Server    │
-│  - Tools        │
+│  VibeTasks MCP  │
+│  - 11 Tools     │
 │  - Resources    │
-│  - Hooks        │
+│  - Status Flow  │
+│  - Context Notes│
 └────────┬────────┘
          │
 ┌────────▼────────┐
-│  @taskflow/     │
-│   mcp-core      │
+│  @vibetasks/    │
+│     core        │
 └────────┬────────┘
          │
 ┌────────▼────────┐
@@ -301,6 +412,22 @@ CLAUDE_HOOK_TYPE=SessionStart node dist/index.js
 └─────────────────┘
 ```
 
+## Tool Reference
+
+| Tool | Description |
+|------|-------------|
+| `create_task` | Create a new task (with optional parent for subtasks) |
+| `create_task_with_subtasks` | Create parent + multiple subtasks in one call |
+| `list_tasks` | Get tasks with status filter (todo, vibing, done) |
+| `update_task` | Update task properties including status |
+| `complete_task` | Mark task as done |
+| `start_vibing` | Mark task as in progress with optional context |
+| `get_vibing_tasks` | Get all tasks currently in progress |
+| `set_context_notes` | Update "where I left off" notes |
+| `delete_task` | Delete a task |
+| `search_tasks` | Search tasks by title |
+| `log_ai_session` | Log an AI coding session |
+
 ## Contributing
 
 See [main README](../../README.md) for contribution guidelines.

package/package.json

@@ -1,11 +1,39 @@
 {
   "name": "@vibetasks/mcp-server",
-  "version": "0.1.0",
-  "description": "VibeTasks MCP Server for Claude Code and other AI coding tools",
+  "version": "0.2.1",
+  "description": "VibeTasks MCP Server for Claude Code, Cursor, and AI coding tools. Status-based task management: todo → vibing → done.",
+  "author": "Vyas",
+  "license": "MIT",
   "type": "module",
+  "main": "./dist/index.js",
   "bin": {
     "vibetasks-mcp": "./dist/index.js"
   },
+  "files": [
+    "dist"
+  ],
+  "keywords": [
+    "vibetasks",
+    "vibe",
+    "vibecoding",
+    "mcp",
+    "mcp-server",
+    "model-context-protocol",
+    "claude-code",
+    "cursor",
+    "ai-tools",
+    "task-management",
+    "productivity"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/vyassathya/vibetasks.git",
+    "directory": "apps/mcp-server"
+  },
+  "homepage": "https://vibetasks.dev",
+  "bugs": {
+    "url": "https://github.com/vyassathya/vibetasks/issues"
+  },
   "scripts": {
     "dev": "tsx src/index.ts",
     "build": "tsup src/index.ts --format esm --clean --outDir dist --shims",
@@ -17,7 +45,7 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^0.5.0",
-    "@vibetasks/core": "^0.1.0",
+    "@vibetasks/core": "^0.2.0",
     "zod": "^3.22.0"
   },
   "devDependencies": {

package/config/claude-code.json

@@ -1,38 +0,0 @@
-{
-  "mcpServers": {
-    "taskflow": {
-      "command": "node",
-      "args": [
-        "REPLACE_WITH_PATH_TO_DIST/index.js"
-      ],
-      "env": {
-        "TASKFLOW_SUPABASE_URL": "https://cbkkztbcoitrfcleghfd.supabase.co",
-        "TASKFLOW_SUPABASE_KEY": "REPLACE_WITH_ANON_KEY"
-      }
-    }
-  },
-  "hooks": {
-    "SessionStart": [
-      {
-        "type": "command",
-        "command": "node",
-        "args": ["REPLACE_WITH_PATH_TO_DIST/index.js"],
-        "env": {
-          "CLAUDE_HOOK_TYPE": "SessionStart",
-          "TASKFLOW_SUPABASE_URL": "https://cbkkztbcoitrfcleghfd.supabase.co"
-        }
-      }
-    ],
-    "Stop": [
-      {
-        "type": "command",
-        "command": "node",
-        "args": ["REPLACE_WITH_PATH_TO_DIST/index.js"],
-        "env": {
-          "CLAUDE_HOOK_TYPE": "SessionEnd",
-          "TASKFLOW_SUPABASE_URL": "https://cbkkztbcoitrfcleghfd.supabase.co"
-        }
-      }
-    ]
-  }
-}

package/scripts/install.js

@@ -1,119 +0,0 @@
-#!/usr/bin/env node
-
-import fs from 'fs/promises';
-import path from 'path';
-import os from 'os';
-import { fileURLToPath } from 'url';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-
-async function install() {
-  try {
-    // Determine Claude Code config location
-    const configHome = process.env.XDG_CONFIG_HOME || path.join(os.homedir(), '.config');
-    const claudeConfigDir = path.join(configHome, 'claude-code');
-    const claudeConfigPath = path.join(claudeConfigDir, 'config.json');
-
-    // Get absolute path to MCP server
-    const mcpServerPath = path.resolve(__dirname, '..', 'dist', 'index.js');
-
-    // Read Supabase credentials from web app .env
-    const webEnvPath = path.resolve(__dirname, '..', '..', '..', 'apps', 'web', '.env.local');
-    let supabaseUrl = 'https://cbkkztbcoitrfcleghfd.supabase.co';
-    let supabaseKey = '';
-
-    try {
-      const envContent = await fs.readFile(webEnvPath, 'utf-8');
-      const urlMatch = envContent.match(/NEXT_PUBLIC_SUPABASE_URL=(.+)/);
-      const keyMatch = envContent.match(/NEXT_PUBLIC_SUPABASE_ANON_KEY=(.+)/);
-
-      if (urlMatch) supabaseUrl = urlMatch[1].trim();
-      if (keyMatch) supabaseKey = keyMatch[1].trim();
-    } catch (error) {
-      console.warn('⚠️  Could not read .env.local, using defaults');
-    }
-
-    // Read existing config or create new
-    let config = {};
-    try {
-      const existingConfig = await fs.readFile(claudeConfigPath, 'utf-8');
-      config = JSON.parse(existingConfig);
-    } catch (error) {
-      // Config doesn't exist, will create new
-      await fs.mkdir(claudeConfigDir, { recursive: true });
-    }
-
-    // Add TaskFlow MCP server
-    if (!config.mcpServers) config.mcpServers = {};
-
-    config.mcpServers.taskflow = {
-      command: 'node',
-      args: [mcpServerPath],
-      env: {
-        TASKFLOW_SUPABASE_URL: supabaseUrl,
-        TASKFLOW_SUPABASE_KEY: supabaseKey
-      }
-    };
-
-    // Add hooks
-    if (!config.hooks) config.hooks = {};
-
-    config.hooks.SessionStart = config.hooks.SessionStart || [];
-    config.hooks.Stop = config.hooks.Stop || [];
-
-    // Add SessionStart hook if not already present
-    const sessionStartExists = config.hooks.SessionStart.some(
-      h => h.command === 'node' && h.args?.[0] === mcpServerPath
-    );
-
-    if (!sessionStartExists) {
-      config.hooks.SessionStart.push({
-        type: 'command',
-        command: 'node',
-        args: [mcpServerPath],
-        env: {
-          CLAUDE_HOOK_TYPE: 'SessionStart',
-          TASKFLOW_SUPABASE_URL: supabaseUrl
-        }
-      });
-    }
-
-    // Add SessionEnd (Stop) hook if not already present
-    const sessionEndExists = config.hooks.Stop.some(
-      h => h.command === 'node' && h.args?.[0] === mcpServerPath
-    );
-
-    if (!sessionEndExists) {
-      config.hooks.Stop.push({
-        type: 'command',
-        command: 'node',
-        args: [mcpServerPath],
-        env: {
-          CLAUDE_HOOK_TYPE: 'SessionEnd',
-          TASKFLOW_SUPABASE_URL: supabaseUrl
-        }
-      });
-    }
-
-    // Write config
-    await fs.writeFile(claudeConfigPath, JSON.stringify(config, null, 2), 'utf-8');
-
-    console.log('✓ TaskFlow MCP server installed successfully!');
-    console.log('\nConfiguration written to:', claudeConfigPath);
-    console.log('\nMCP Server path:', mcpServerPath);
-    console.log('\n📝 Next steps:');
-    console.log('1. Restart Claude Code');
-    console.log('2. Type "@" in chat to see TaskFlow tools');
-    console.log('3. Tools available: create_task, get_tasks, complete_task, etc.');
-    console.log('\n💡 Hooks installed:');
-    console.log('- SessionStart: Loads your tasks automatically');
-    console.log('- SessionEnd: Auto-logs completed work as tasks');
-
-  } catch (error) {
-    console.error('❌ Installation failed:', error.message);
-    process.exit(1);
-  }
-}
-
-install();