What can you do with this server?

The AiDD MCP Server is an ADHD-optimized productivity platform that connects Claude to your AiDD account for managing notes, action items, and tasks with AI-powered features. Core Capabilities: * Authentication: Browser-based OAuth (Google, Microsoft, Apple, or email/password) with automatic token refresh and session status checking * Notes Management: Create, read, update, delete, and search notes with full-text search, categorization, tags, and pagination * AI-Powered Action Items: Extract action items from notes/text using Google Gemini with confidence scoring, priority levels, and due dates * ADHD-Optimized Tasks: Convert action items into manageable subtasks with automatic time estimates, energy requirements, dependency tracking, and AI prioritization based on urgency, importance, energy levels, and ADHD compatibility * Async AI Processing: Background processing for AI operations with job monitoring via check_ai_jobs tool * ChatGPT UI Widgets: Interactive widgets for task dashboards, action items, energy selectors, quick capture forms, dependency graphs, and focus mode * Integrations: Connect with Google Tasks, Microsoft To Do, Trello, Todoist, Notion, TickTick, and Evernote * Universal Access: Works with Claude on web browsers, mobile apps, and desktop applications via URL connection Workflow: Complete productivity workflow from capturing notes → extracting action items → converting to manageable tasks → AI-powered prioritization → execution guidance based on energy levels and time of day. Security & Privacy: Robust OAuth 2.0 authentication, encryption, GDPR/CCPA/SOC 2 Type II compliance. User data is not used for AI training or sold. Subscription Tiers: Free tier with limited AI features and PRO tier with unlimited AI operations and auto-scoring. Note: The server schema shows 4 basic tools (connect, disconnect, status, start_workflow), but the full implementation (v4.4.0) provides 18 comprehensive tools across notes (5), action items (5), tasks (7), and AI jobs (1), plus 8 ChatGPT UI widget resources.

Which integrations are available for this server?

Provides comprehensive Apple Notes integration including creating, searching, reading, updating, and deleting notes, with folder management and tag support. Enables synchronization of AI-extracted action items and tasks to Evernote. Enables synchronization of AI-extracted action items and tasks to Google Tasks. Enables synchronization of AI-extracted action items and tasks to Notion. Enables synchronization of AI-extracted action items and tasks to TickTick. Enables synchronization of AI-extracted action items and tasks to Todoist. Enables synchronization of AI-extracted action items and tasks to Trello boards.

How do I use AiDD MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AiDD MCP Server extract action items from my meeting notes and prioritize them" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

AiDD MCP Server

by AiDD-app

Overview Schema Related Servers Score Discussions

TypeScript

Local

The AiDD MCP Server is an ADHD-optimized productivity platform that connects Claude to your AiDD account for managing notes, action items, and tasks with AI-powered features.

Core Capabilities:

Authentication: Browser-based OAuth (Google, Microsoft, Apple, or email/password) with automatic token refresh and session status checking
Notes Management: Create, read, update, delete, and search notes with full-text search, categorization, tags, and pagination
AI-Powered Action Items: Extract action items from notes/text using Google Gemini with confidence scoring, priority levels, and due dates
ADHD-Optimized Tasks: Convert action items into manageable subtasks with automatic time estimates, energy requirements, dependency tracking, and AI prioritization based on urgency, importance, energy levels, and ADHD compatibility
Async AI Processing: Background processing for AI operations with job monitoring via check_ai_jobs tool
ChatGPT UI Widgets: Interactive widgets for task dashboards, action items, energy selectors, quick capture forms, dependency graphs, and focus mode
Integrations: Connect with Google Tasks, Microsoft To Do, Trello, Todoist, Notion, TickTick, and Evernote
Universal Access: Works with Claude on web browsers, mobile apps, and desktop applications via URL connection

Workflow: Complete productivity workflow from capturing notes → extracting action items → converting to manageable tasks → AI-powered prioritization → execution guidance based on energy levels and time of day.

Security & Privacy: Robust OAuth 2.0 authentication, encryption, GDPR/CCPA/SOC 2 Type II compliance. User data is not used for AI training or sold.

Subscription Tiers: Free tier with limited AI features and PRO tier with unlimited AI operations and auto-scoring.

Note: The server schema shows 4 basic tools (connect, disconnect, status, start_workflow), but the full implementation (v4.4.0) provides 18 comprehensive tools across notes (5), action items (5), tasks (7), and AI jobs (1), plus 8 ChatGPT UI widget resources.

@aidd-app/mcp

Official AiDD MCP Web Connector - ADHD-optimized productivity platform accessible from Claude web, mobile, and desktop.

License: MIT Version

🌐 Universal Access

Works everywhere Claude works:

✅ Claude.ai (desktop browsers)
✅ Claude mobile apps (iOS/Android)
✅ Claude Desktop (all platforms)
✅ ChatGPT Apps (with rich UI widgets)

Simply connect via URL - no local installation required.

Related MCP server: Apple MCP - Enhanced Edition

Features

📝 Notes Management

List, read, create, update, and delete notes in your AiDD account
Full-text search and pagination
Categorization (work/personal) and tags
Batch delete support

✅ Action Items (AI-Powered)

AI Extraction: Extract action items from notes or text using Google Gemini
List, read, update, and delete action items with priority/due dates
Confidence scoring for each extracted item
Batch delete support

🎯 ADHD-Optimized Tasks

AI Task Breakdown: Convert action items into manageable subtasks
- Automatic time estimates
- Energy level requirements
- Dependency tracking
- Task type classification
AI Prioritization: Smart task scoring
- Urgency × Importance × Energy × ADHD compatibility
- Time-of-day optimization
- Personalized recommendations
Full CRUD: Create, read, update, and delete tasks
Batch delete support

🚀 Async AI Processing

AI operations run in background by default for better UX
No timeout issues for large data sets
New: check_ai_jobs tool to monitor job progress in real-time
Check results with list_tasks or list_action_items
Optional waitForCompletion parameter for small batches

⚡ Auto AI Scoring (New in v4.3.22)

For paid users (PRO/PREMIUM), AI scoring is automatically triggered after task conversion:

MCP: Always auto-scores after conversion
Web/iOS: Auto-scores when converting more than 1 action item

This means your tasks are immediately prioritized without needing a separate scoring step!

🖼️ ChatGPT UI Widgets (New in v4.4.0)

Rich interactive widgets for ChatGPT Apps integration:

Widget	Description
Task Dashboard	Visual task prioritization with AI scores
Action Items	AI-extracted items with confidence scores
Energy Selector	Task selection by energy level
Quick Capture	Fast task creation form
Dependency Graph	Visual task dependencies
Focus Mode	Pomodoro-style timer
AI Scoring	Score distribution and insights

Widgets are served as MCP resources with text/html+skybridge MIME type for native ChatGPT integration.

🔐 Authentication

Browser-based OAuth (Google, Microsoft, Apple)
Email/password sign-in
Automatic token refresh
Secure cloud storage

📱 Integrations

Google Tasks
Microsoft To Do
Trello, Todoist, Notion
TickTick, Evernote

Quick Start

Production URL: https://mcp.aidd.app/mcp

Open claude.ai → Settings
Navigate to "Connectors" or "MCP"
Click "Add Connector"
Enter URL: https://mcp.aidd.app/mcp
Save

That's it! Now use it:

You: connect
Claude: [opens browser for authentication]

You: list my tasks
Claude: [shows your AiDD tasks]

You: score my tasks and tell me what to work on next
Claude: [AI analyzes and prioritizes your tasks]

📚 Realistic Usage Examples

Example 1: Morning Task Planning with Energy Levels

Scenario: You want to plan your workday based on your current energy level.

You: "I just woke up and have high energy. What should I work on this morning?"

Claude: [Uses score_tasks with timeOfDay="morning", considerCurrentEnergy=true]

Response:
🎯 Tasks Scored & Prioritized

Top Priority Tasks (Next 2 Hours):
1. Complete quarterly performance reviews (Score: 95/100)
   • Urgency: 9/10
   • Importance: 9/10
   • Energy Match: High ✓
   📝 Best tackled now while your focus is sharp

2. Draft project proposal for Q2 (Score: 89/100)
   • Urgency: 7/10
   • Importance: 9/10
   • Time: 45 min
   📝 Complex task - ideal for morning energy

🌅 Morning Schedule (High Energy):
  • Complete quarterly performance reviews
  • Draft project proposal for Q2
  • Review architecture decisions

Example 2: Meeting Notes to Action Items

Scenario: You just finished a team meeting and have raw notes to process.

You: "I just finished a team meeting. Here are my notes:
     - John will send the budget report by Friday
     - Need to schedule client demo for next week
     - Sarah mentioned the API is having issues, investigate
     - Book conference room for quarterly planning
     - Follow up with marketing on campaign results"

Claude: [Uses extract_action_items with source="text"]

Response:
🔍 Action Items Extracted

Summary:
• Source: provided text
• Extraction mode: adhd-optimized
• Action items found: 5

Extracted Action Items:
1. Follow up on budget report from John
   • Priority: high
   • Category: work
   • Confidence: 92%
   • Due: Friday

2. Schedule client demo
   • Priority: high
   • Category: work
   • Confidence: 95%
   • Due: Next week

3. Investigate API issues
   • Priority: high
   • Category: work
   • Confidence: 88%
   • Tags: technical, bug

4. Book conference room for quarterly planning
   • Priority: medium
   • Category: work
   • Confidence: 90%

5. Follow up with marketing on campaign results
   • Priority: medium
   • Category: work
   • Confidence: 87%

Action items have been saved to your AiDD account.

Example 3: Converting Action Items to ADHD-Friendly Tasks

Scenario: You have action items but need them broken down into manageable steps.

You: "Convert my action items to tasks with ADHD-optimized breakdown"

Claude: [Uses convert_to_tasks with breakdownMode="adhd-optimized"]

Response:
🚀 AI Conversion Started

Converting 5 action items to ADHD-optimized tasks in the background.

What's happening:
• AI is breaking down action items into manageable tasks
• Tasks are being optimized for ADHD-friendly execution
• Each action item may generate multiple subtasks

✨ Auto AI Scoring: Enabled (PRO subscription detected)
• Your tasks will be automatically prioritized after conversion

Check your results:
⏱️ Check back in 2-3 minutes - use the `list_tasks` tool to see your converted tasks.
💡 Or use `check_ai_jobs` to monitor progress in real-time.

Example 4: Monitoring AI Job Progress

Scenario: You started a large conversion and want to check progress.

You: "Check the status of my AI jobs"

Claude: [Uses check_ai_jobs]

Response:
📊 AI Jobs (2 active)

⏳ **🔄 Task Conversion**
   • ID: `job_abc123`
   • Status: processing (75%)

✅ **🎯 Task Scoring**
   • ID: `job_def456`
   • Status: completed

💡 Tip: Use `check_ai_jobs` with a specific `jobId` to get detailed status.

Example 5: Updating and Deleting Items

Scenario: You need to modify or clean up your task list.

You: "Mark task abc123 as completed and delete the old action items I'm done with"

Claude: [Uses update_task to mark complete, then delete_action_items]

Response:
✅ Task Updated

Updated task: Complete quarterly report
• ID: abc123
• Status: ✅ Completed
• Updated: 12/02/2025, 5:30 PM

🗑️ Action Items Deleted

Successfully deleted 3 action items.

🔗 Also deleted 5 derived tasks.

Example 6: Weekly Review and Planning

Scenario: End of week review to see accomplishments and plan ahead.

You: "Help me do a weekly review. Show me what I accomplished and what's pending for next week."

Claude: [Uses list_tasks, list_action_items, then score_tasks]

Response:
📊 Weekly Review

✅ Completed This Week:
• 12 tasks completed
• 8 action items resolved
• Highlights:
  - Finished quarterly report (Score: 95)
  - Deployed API fix (Score: 88)
  - Client presentation delivered (Score: 92)

📋 Pending Action Items (7):
• High Priority: 2
• Medium Priority: 4
• Low Priority: 1

🎯 Next Week's Top Priorities:
1. Prepare board presentation (Score: 94/100)
   • Due: Tuesday
   • Energy: High required
   • Time: 2 hours

2. Complete performance reviews (Score: 91/100)
   • Due: Friday
   • Energy: Medium
   • Time: 45 min each

3. Follow up on vendor contracts (Score: 85/100)
   • Due: Wednesday
   • Energy: Low
   • Time: 30 min

💡 Recommendation: Block Tuesday morning for the board
presentation while your energy is highest.

Available Tools

Notes (5 tools)

Tool	Description	Type
`list_notes`	Browse notes (sortBy: createdAt/updatedAt/title)	Read
`read_note`	Read specific note by ID	Read
`create_note`	Create new note with title, content, tags, category	Write
`update_note`	Update existing note (title, content, tags, category)	Write
`delete_notes`	Delete one or more notes by ID	Destructive

Action Items (5 tools)

Tool	Description	Type
`list_action_items`	Browse action items with sorting	Read
`read_action_item`	Read specific action item by ID	Read
`extract_action_items`	AI-powered extraction from notes or text	Write
`update_action_item`	Update existing action item (title, priority, due date, etc.)	Write
`delete_action_items`	Delete action items and their derived tasks	Destructive

Tasks (7 tools)

Tool	Description	Type
`list_tasks`	Browse tasks with AI scores	Read
`read_task`	Read specific task by ID	Read
`create_task`	Create a new task manually	Write
`convert_to_tasks`	Convert action items to ADHD-optimized tasks (async)	Write
`score_tasks`	AI-powered task prioritization (async)	Write
`update_task`	Update existing task (title, energy, time, completed, etc.)	Write
`delete_tasks`	Delete one or more tasks by ID	Destructive

AI Jobs (1 tool)

Tool	Description	Type
`check_ai_jobs`	Monitor AI job progress (extraction, conversion, scoring)	Read

Authentication (1 tool)

Tool	Description	Type
`status`	Check authentication status and account info	Read

Total: 18 tools (9 read-only, 6 write, 3 destructive)

Architecture

┌─────────────────┐
│   Claude        │ (web/mobile/desktop)
│   User          │
└────────┬────────┘
         │ HTTPS/SSE
         ↓
┌─────────────────┐
│   AiDD MCP      │ Cloud Run (auto-scale 1-10)
│   Web Connector │ Node.js 20, Express, CORS
└────────┬────────┘
         │ REST API
         ↓
┌─────────────────┐
│   AiDD Backend  │ Cloud Run (production HA)
│   - Firestore   │ - Notes, Tasks, Action Items
│   - Redis       │ - Sessions, Cache
│   - Gemini AI   │ - Extraction, Conversion, Scoring
└─────────────────┘

ChatGPT Apps Integration

ChatGPT App
    └── Connects to MCP Server: https://mcp.aidd.app
            ├── Discovers tools (list_tasks, score_tasks, etc.)
            │   └── Each tool has _meta.ui_template linking to widget
            └── Discovers resources
                ├── aidd://notes (JSON data)
                ├── aidd://tasks (JSON data)
                └── aidd://widgets/* (text/html+skybridge)
                        └── ChatGPT loads in iframe + injects window.openai

Widget Resource	Tool Mapping
`aidd://widgets/task-dashboard`	`list_tasks`
`aidd://widgets/action-items`	`extract_action_items`, `convert_to_tasks`
`aidd://widgets/ai-scoring`	`score_tasks`, `check_ai_jobs`
`aidd://widgets/quick-capture`	`create_task`

Tech Stack

Runtime: Node.js 20
Framework: Express.js
Protocol: MCP over HTTP/SSE (Streamable HTTP Transport)
Transport: Server-Sent Events
Auth: OAuth 2.0 with PKCE (S256)
AI: Google Gemini 2.5 Pro & 2.5 Flash

Testing the Connector

You can verify the connector is running:

# Health check
curl https://mcp.aidd.app/health

# MCP endpoint info
curl https://mcp.aidd.app/mcp

# OAuth discovery
curl https://mcp.aidd.app/.well-known/oauth-authorization-server

Subscription Tiers

Tier	AI Scoring	AI Extractions	Task Conversions	Auto-Scoring	Cooldown
FREE	1/month	3/week	1/week	❌	5 min
PRO	10/day	200/week	200/week	✅	None

PRO Plans: $4.99/month or $49.99/year (save $10)

Upgrade at: https://aidd.app/upgrade

Security & Privacy

Authentication & Data Protection

Feature	Implementation
OAuth 2.0	Authorization Code Flow with PKCE (S256)
Token Security	JWT with 30-day expiry, auto-refresh
Transport	HTTPS/TLS 1.3 for all communication
CORS	Restricted to `claude.ai`, `.claude.ai`, `.anthropic.com`
Data at Rest	AES-256 encryption (Google Cloud)
Rate Limiting	Token bucket algorithm per subscription tier
Request Signing	HMAC verification for API calls

Compliance

Standard	Status
GDPR	✅ Full compliance (EU data protection)
CCPA	✅ Full compliance (California privacy)
SOC 2 Type II	✅ Certified infrastructure (Google Cloud)

Privacy Policy

AiDD processes your notes, tasks, and action items to provide AI-powered productivity features. We take your privacy seriously:

What We Collect

Account Information: Email address, authentication tokens
Content Data: Notes, action items, tasks you create or import
Usage Data: Feature usage for improving the service (anonymized)

How We Use Your Data

AI Processing: Notes → Action items → Tasks (on-demand only)
Storage: Encrypted in your personal account
Analytics: Anonymized usage patterns (opt-out available)

What We DON'T Do

❌ No AI Training: Your data is NEVER used to train AI models (including Google Gemini)
❌ No Selling: Your data is NEVER sold to third parties
❌ No Advertising: No targeted ads based on your content
❌ No Retention: AI processing is ephemeral, not stored in AI systems

Your Rights

Access: Export all your data at any time
Deletion: Request complete data deletion (GDPR Article 17)
Portability: Download your data in standard formats
Correction: Update or correct your information
Objection: Opt-out of non-essential processing

Data Processing Details

Data Type	Processing	Retention	AI Involvement
Notes	Stored encrypted	Until deleted	Extraction only (not stored in AI)
Action Items	Generated by AI	Until deleted	Created by Gemini, stored in your account
Tasks	AI-scored	Until deleted	Scores calculated on-demand
Auth Tokens	OAuth 2.0	30 days	None
Passwords	NOT stored	N/A	None (OAuth only)

Security Measures

🔐 End-to-end encryption for sensitive data
🔒 Secrets management via Google Secret Manager
🛡️ DDoS protection via Cloud Armor
📝 Audit logging with 30-day retention
🔍 Regular security audits and penetration testing

📋 Full Privacy Policy: https://aidd.app/privacy 📜 Terms of Service: https://aidd.app/terms

For Anthropic Reviewers

Test Account

A dedicated test account is available for Anthropic MCP review:

Field	Value
Email	`[TEST_EMAIL_REDACTED]`
Password	`[REDACTED]`
Subscription	PREMIUM (unlimited)
Status	✅ Active

Full testing instructions: TEST_CREDENTIALS.md

Pre-loaded Test Data

16 Notes - Various categories and tags
13 Action Items - Mixed priorities with confidence scores
13 Tasks - All with AI scores (relevance, impact, urgency)

Support During Review

Email: marc@aidd.app
Subject: "Anthropic MCP Review - [Issue]"
Response Time: < 2 hours (9am-6pm PST)

Troubleshooting

"Connection Failed"

Check health: curl https://mcp.aidd.app/health
Verify URL: https://mcp.aidd.app/mcp
Try removing and re-adding the connector

"Authentication Error"

Browser popup blocked? Allow popups for claude.ai
Try incognito mode (clear cookies)
Check if test account credentials are correct

"Rate Limit Exceeded"

Check quota with status tool
Upgrade at https://aidd.app/upgrade

Why Web Connector?

vs Desktop Extension:

Feature	Desktop	Web Connector
Platforms	macOS/Windows/Linux only	All platforms
Installation	Local install required	Just add URL
Updates	Manual	Automatic
Mobile	❌	✅

vs Separate MCPs:

Combine AiDD with other MCP connectors
Example: Use with Apple Notes MCP for macOS
Claude orchestrates between multiple MCPs automatically

Support

🌐 Website: aidd.app
📧 Email: support@aidd.app
🐛 Issues: GitHub
📚 Docs: docs.aidd.app

Contributing

Contributions welcome! See CONTRIBUTING.md

License

MIT © AiDD Team

Changelog

v4.4.0 (2025-12-19)

🖼️ New: ChatGPT UI Widgets - Rich interactive components for ChatGPT Apps
- Task Priority Dashboard with AI scores
- Action Item Extraction Preview with confidence
- Energy-Based Task Selector
- Quick Capture Form
- Dependency Graph visualization
- Focus Mode timer
- AI Scoring Results Card
📦 New: MCP Resources for UI widgets (aidd://widgets/*)
- Self-contained HTML with inlined CSS/JS
- text/html+skybridge MIME type for ChatGPT integration
- Tool-to-widget linking via _meta.ui_template
🔧 Architecture: UI bundled directly into MCP server
- No separate hosting required
- Automatic discovery by ChatGPT Apps
📊 Total tools: 18 (unchanged) + 8 widget resources

v4.3.22 (2025-12-02)

🔍 New Tool: check_ai_jobs - Monitor AI job progress in real-time
- Check specific job by ID or list all active jobs
- Shows job type, status, progress percentage, and timestamps
- Provides helpful next steps based on job status
⚡ Auto AI Scoring: Paid users (PRO/PREMIUM) now get automatic task scoring after conversion
- MCP: Always auto-scores after task conversion
- Web/iOS: Auto-scores when converting more than 1 action item
- No separate scoring step needed - tasks are prioritized automatically
📊 Total tools: 17 → 18

v4.3.18 (2025-11-30)

🔗 Cascade Delete: delete_action_items now automatically deletes all tasks derived from those action items
- Prevents orphaned tasks when cleaning up action items
- Response shows count of both deleted action items and derived tasks

v4.3.7 (2025-11-28)

🔒 Security: Added MCP safety annotations to all 20 tools
- readOnlyHint: true for read-only operations (list_*, read_*, status)
- destructiveHint: true for delete operations (delete_notes, delete_action_items, delete_tasks)
- readOnlyHint: false, destructiveHint: false for write operations
🔐 OAuth: Added Claude callback URLs to allowlist (localhost:6274, claude.ai, claude.com)
🌐 HEAD: Added HEAD request handlers for OAuth endpoints

v4.1.1 (2025-11-25)

✏️ New: update_note - Update existing notes (title, content, tags, category)
🗑️ New: delete_notes - Delete one or more notes (batch support)
✏️ New: update_action_item - Update action items (title, priority, due date, completed status)
🗑️ New: delete_action_items - Delete one or more action items (batch support)
✏️ New: update_task - Update tasks (title, energy, time, type, completed status)
🗑️ New: delete_tasks - Delete one or more tasks (batch support)
📊 Total tools: 11 → 17

v4.1.0 (2025-11-24)

🚀 New: Async mode for AI operations (default)
⚡ Improved: convert_to_tasks runs in background, no timeout issues
⚡ Improved: score_tasks runs in background, handles large task lists
🔧 New: waitForCompletion parameter for synchronous mode
📝 Improved: Better response messages with "check in 2-3 minutes" guidance

v4.0.2 (2025-11-24)

📚 Docs: Added 5 realistic usage examples for Anthropic review
🔒 Privacy: Enhanced privacy policy section with full details inline
🐛 Fix: AI scores display (relevance, impact, urgency)
🐛 Fix: Task scoring deviceId requirement

v4.0.0 (2025-01-22) - Web Connector Edition

🌐 Breaking: Transitioned from stdio to HTTP/SSE transport
📱 New: Universal access (web, mobile, desktop)
☁️ New: Hosted service with auto-scaling
🔒 Enhanced: CORS for Claude domains
❌ Removed: Apple Notes integration (use separate MCP)
⚡ Improved: Cloud-native observability

v3.0.0 (2025-01-15)

CRUD-based architecture
11 comprehensive tools
Direct backend integration
Enhanced AI features

v2.0.0 (2025-01-10)

Browser-based OAuth
Multi-provider sign-in

v1.0.0 (2025-01-05)

Initial release

Made with ❤️ by the AiDD Team for the ADHD community

Transform your notes into actionable tasks, from anywhere, on any device.

Available Tools

4 tools

connectB

Connect to AiDD account via browser authentication

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'browser authentication' which implies user interaction, but doesn't describe what happens during connection (e.g., opens browser window, requires user login, stores session tokens), what permissions are needed, or error conditions. The description is minimal and lacks important behavioral context for an authentication tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that communicates the core purpose without any wasted words. It's appropriately sized for a zero-parameter authentication tool and front-loads the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an authentication tool with no annotations and no output schema, the description is insufficient. It doesn't explain what successful connection enables, what data is returned (tokens, user info), error handling, or how the connection persists for subsequent tool calls. Given the complexity of authentication flows and the lack of structured documentation, the description should provide more complete context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, and the schema already fully documents this. No additional parameter information is needed or provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Connect') and target resource ('AiDD account'), specifying the authentication method ('via browser authentication'). It distinguishes from sibling 'disconnect' by being the opposite operation. However, it doesn't fully differentiate from 'start_workflow' or 'status' in terms of when to use this specific connection method.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives or prerequisites. It doesn't mention whether this should be used for initial setup, re-authentication, or when other tools require authentication. With siblings like 'disconnect', 'start_workflow', and 'status', there's no indication of sequencing or dependencies.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

disconnectB

Disconnect from AiDD account

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states the action without disclosing behavioral traits. It doesn't mention effects (e.g., session termination, data persistence), authentication changes, or error conditions, leaving significant gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and resource, making it immediately understandable without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral impact, success/error responses, and context for use with siblings, failing to compensate for the missing structured information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, meeting the baseline for parameterless tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Disconnect') and target resource ('from AiDD account'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'connect' beyond the obvious opposite action, missing explicit comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives or prerequisites. The description implies usage after being connected, but doesn't specify conditions, exclusions, or relationships with siblings like 'connect'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

start_workflowC

Start the AiDD workflow

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Start the AiDD workflow', implying a mutation or action, but does not describe what starting entails, potential side effects, permissions needed, or response behavior, leaving significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no wasted words. It is front-loaded and appropriately sized for a tool with no parameters, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (implied mutation with no annotations) and lack of output schema, the description is incomplete. It does not explain what 'starting' the workflow does, what the outcome is, or any behavioral traits, failing to provide sufficient context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%, so no parameter information is needed. The description does not add parameter details, but this is appropriate given the lack of parameters, aligning with the baseline for zero parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Start the AiDD workflow' states a verb ('Start') and resource ('AiDD workflow'), providing a basic purpose. However, it lacks specificity about what the workflow does or how it differs from sibling tools like 'connect' or 'disconnect', making it somewhat vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'connect' or 'disconnect'. The description does not mention prerequisites, context, or exclusions, leaving the agent without clear usage instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

statusB

Check authentication status

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Check authentication status' implies a read-only operation that verifies authentication state, but it doesn't specify what constitutes 'status' (e.g., valid/invalid, token expiration, permissions), whether it requires any authentication itself, what happens on failure, or what format the response takes. For a tool with zero annotation coverage, this leaves significant behavioral questions unanswered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description 'Check authentication status' is a single, efficient sentence that communicates the core purpose without any wasted words. It's appropriately sized for a simple, parameterless tool and is front-loaded with the essential action. Every word earns its place in this minimal but complete phrase.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is adequate but has clear gaps. It states what the tool does but doesn't provide enough context about when to use it, what the output looks like, or behavioral characteristics. For a status-checking tool in an authentication context, more guidance about typical usage patterns and expected outcomes would be helpful, though the minimal nature of the tool makes this less critical than for complex operations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the absence of parameters. The description doesn't need to add parameter information, and it appropriately doesn't mention any parameters. The baseline for 0 parameters with high schema coverage is 4, as the description correctly focuses on purpose rather than parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Check authentication status' clearly states the tool's purpose with a specific verb ('Check') and resource ('authentication status'). It distinguishes from siblings like 'connect' (establish connection) and 'disconnect' (terminate connection) by focusing on verification rather than connection management. However, it doesn't explicitly differentiate from 'start_workflow' which might involve authentication checks as part of a larger process.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't indicate whether this should be used before 'connect', after 'disconnect', or as a periodic verification during 'start_workflow'. There's no mention of prerequisites, error conditions, or typical usage patterns, leaving the agent to infer context from tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: connect and disconnect handle authentication lifecycle, start_workflow initiates the core functionality, and status checks the current state. There is no ambiguity between these four operations.

Naming Consistency5/5

All tools follow a consistent verb-based naming pattern (connect, disconnect, start_workflow, status) using snake_case throughout. The naming is predictable and readable without any deviations in style.

Tool Count5/5

With 4 tools, this server is well-scoped for its apparent authentication and workflow management domain. Each tool earns its place, providing essential operations without bloat or missing elements for a minimal viable surface.

Completeness4/5

The toolset covers the core authentication lifecycle (connect, disconnect, status) and workflow initiation (start_workflow), which is complete for a basic interface. A minor gap exists in lacking tools for managing workflows after starting (e.g., stop, monitor, or list workflows), but agents can likely work with this minimal set.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

CalmLoop Task Manager
in.calmloop
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Project Management Note Taking
1
Salta
app.getsalta
Mobile-first AI life planner — turn goals into daily, synced tasks from your AI assistant.
Project Management Workplace & Productivity Calendar Management
21
Bubbl
io.github.bubbl-ai
AI teammate for tasks: builds your list from meetings, email and chats, and checks off done work.
Project Management App Automation Workplace & Productivity
2
Recordo: Task Planner & Notes
app.recordo.api
Brain dump, routines, task planning, focus, and instant thought retrieval
Note Taking Knowledge & Memory Project Management
2

Related MCP Servers

Apple Notes MCP Server
Note Taking Autonomous Agents
Siddhant-K-code
A
license
D
quality
B
maintenance
Enables interaction with Apple Notes via natural language, supporting note creation, search, and retrieval with iCloud integration for seamless note management.
Updated 22 days ago (2026-08-13 07:33 UTC)
3
17
24
MIT
Apple MCP - Enhanced Edition
App Automation Communication Calendar Management
Ayaanisthebest
A
license
Not graded
quality
D
maintenance
Enables AI assistants to interact with native Apple applications including Messages, Notes, Contacts, Mail, Reminders, Calendar, and Maps. Features smart contact resolution, priority-based search, and comprehensive Apple ecosystem integration with enhanced error handling.
Updated a year ago (2025-08-21 04:46 UTC)
192
2
MIT
Task Management MCP Server
Project Management Workplace & Productivity
Aayush9029
A
license
A
quality
F
maintenance
Connects AI assistants to a task management API for creating, updating, and tracking tasks with iPhone notifications.
Updated 5 months ago (2026-03-28 18:46 UTC)
5
46
MIT
Apple MCP
Communication Note Taking Calendar Management
8ncg92gm86-bit
A
license
Not graded
quality
D
maintenance
Integrates with Apple apps on macOS to enable AI-powered automation of Messages, Notes, Contacts, Mail, Reminders, Calendar, and Maps.
Updated 3 months ago (2026-06-03 21:00 UTC)
192
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AiDD-app/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server