Enables user authentication through Google OAuth integration via Kinde, allowing users to log in with their Google accounts to access the todo management system
Provides database persistence for todo management with user data storage, using Neon PostgreSQL for managing users table and todos table with proper relationships
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Todo MCP Server create a todo to finish the quarterly report by Friday"
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.
A complete Model Context Protocol (MCP) server that demonstrates modern web development practices with authentication, billing, and database integration. Perfect for beginners learning full-stack development!
This project creates a Todo Management System that you can interact with through Cursor AI (or any MCP-compatible client). It includes:
Real Authentication with Kinde
Billing System with free tier limits
Database Storage with Neon PostgreSQL
AI Integration through MCP protocol
Web Interface for authentication
Related MCP server: Todo MCP
5 Free Todos for new users
Upgrade to Paid for unlimited todos
Real Authentication with Google/social login
Database Persistence with PostgreSQL
AI Chat Integration through Cursor
Session Management with secure cookies
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Cursor AI │ │ MCP Server │ │ Kinde Auth │
│ (Your Chat) │◄──►│ (This Project) │◄──►│ (Authentication)│
└─────────────────┘ └──────────────────┘ └─────────────────┘
│
▼
┌──────────────────┐
│ Neon Database │
│ (PostgreSQL) │
└──────────────────┘Before you start, you'll need:
Node.js (version 18 or higher)
A Neon Database account (free)
A Kinde account (free)
Cursor IDE (for MCP integration)
# Clone the repository
git clone <your-repo-url>
cd todo-mcp-server
# Install dependencies
npm install# Run the setup script
chmod +x setup.sh
./setup.shThis creates a .env file with placeholder values.
Go to neon.tech
Create a free account
Create a new database
Copy your connection string
Update your .env file:
DATABASE_URL=postgresql://your-connection-string-hereGo to kinde.com
Create a free account
Create a new application
Copy your credentials
Update your .env file:
KINDE_ISSUER_URL=https://your-domain.kinde.com
KINDE_CLIENT_ID=your_client_id
KINDE_CLIENT_SECRET=your_client_secret# Set up database tables
npm run setup-db# Build the project
npm run build
# Start the MCP server
npm startmcp-todo-rebuild/
├── src/
│ ├── server.ts # Main MCP server
│ ├── kinde-auth-server.ts # Authentication web server
│ └── setup-db.ts # Database setup script
├── dist/ # Compiled JavaScript
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── .env # Environment variables (create this)
└── README.md # This filesrc/server.ts)Handles AI chat commands like "create todo", "list todos"
Manages user authentication and billing
Connects to database for data persistence
src/kinde-auth-server.ts)Provides web interface for login/logout
Handles OAuth flow with Kinde
Automatically creates user database records
src/setup-db.ts)Creates necessary database tables
Sets up indexes for performance
Initializes user and todo schemas
# Terminal 1: Start MCP server
npm start
# Terminal 2: Start auth server
npm run auth-serverAdd this to your Cursor MCP configuration (~/.cursor/mcp.json):
{
"mcpServers": {
"todo-mcp-server": {
"command": "node",
"args": ["dist/server.js"],
"cwd": "/path/to/your/project",
"env": {
"DATABASE_URL": "your_database_url",
"KINDE_ISSUER_URL": "your_kinde_issuer",
"KINDE_CLIENT_ID": "your_client_id",
"KINDE_CLIENT_SECRET": "your_client_secret",
"JWT_SECRET": "your_jwt_secret",
"NODE_ENV": "development"
}
}
}
}Once configured, you can use these commands in Cursor:
login # Get authentication URL
save_token: <token> # Save your login token
list todos # View your todos
create todo # Create a new todo
update todo # Update an existing todo
delete todo # Delete a todo
logout # Log outType "login" in Cursor chat
Click the URL to open authentication page
Login with Google (or other providers)
Copy your token from the success page
Use "save_token" command in Cursor
Start creating todos!
Free Tier: 5 todos per user
Paid Tier: Unlimited todos (upgrade through Kinde portal)
Automatic Tracking: System tracks usage automatically
Upgrade URL: Provided when limit is reached
CREATE TABLE users (
id SERIAL PRIMARY KEY,
user_id TEXT UNIQUE NOT NULL,
name TEXT,
email TEXT,
subscription_status TEXT DEFAULT 'free',
plan TEXT DEFAULT 'free',
free_todos_used INTEGER DEFAULT 0,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);CREATE TABLE todos (
id SERIAL PRIMARY KEY,
user_id TEXT NOT NULL,
title TEXT NOT NULL,
description TEXT,
completed BOOLEAN DEFAULT FALSE,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);# Development
npm run dev # Run MCP server in development
npm run auth-server # Run auth server in development
# Database
npm run setup-db # Set up database tables
# Production
npm run build # Build for production
npm start # Run production serverCreate a .env file with these variables:
# Database
DATABASE_URL=postgresql://user:pass@host:port/db
# Kinde Authentication
KINDE_ISSUER_URL=https://your-domain.kinde.com
KINDE_CLIENT_ID=your_client_id
KINDE_CLIENT_SECRET=your_client_secret
# Security
JWT_SECRET=your_secret_key
# Environment
NODE_ENV=development"No authentication token found"
Make sure you've logged in and saved your token
Check that the auth server is running
"Database connection failed"
Verify your DATABASE_URL is correct
Make sure you've run npm run setup-db
"Kinde authentication failed"
Check your Kinde credentials in .env
Verify your redirect URLs in Kinde dashboard
"MCP server not found in Cursor"
Restart Cursor after updating mcp.json
Check that the server is running with npm start
Run with debug logging:
DEBUG=* npm run devMCP Protocol: How AI assistants interact with tools
OAuth 2.0: Modern authentication flows
PostgreSQL: Database design and queries
TypeScript: Type-safe JavaScript development
Express.js: Web server development
Session Management: User state persistence
Model Context Protocol (MCP): Standard for AI tool integration
OAuth Flow: Secure authentication without passwords
JWT Tokens: Secure user identification
Database Relations: User-todo relationships
Billing Integration: Freemium business models
Once you understand this project, you can:
Add More Features: Categories, due dates, sharing
Improve UI: Better web interface for auth
Add Real Billing: Stripe integration
Deploy: Host on Vercel, Railway, or AWS
Scale: Add caching, load balancing
This is a learning project! Feel free to:
Report bugs
Suggest improvements
Add new features
Create tutorials
MIT License - feel free to use this for learning and projects!
If you get stuck:
Check the troubleshooting section above
Verify all environment variables are set
Make sure all services are running
Check the console for error messages
Remember: This is a learning project designed to teach modern web development concepts. Take your time, experiment, and don't hesitate to explore the code!
Create a new todo item with interactive prompts
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | No | Authentication token from Kinde (optional if saved) | |
| title | No | Title of the todo item | |
| description | No | Optional description of the todo item | |
| completed | No | Completion status of the todo |
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 'interactive prompts' which hints at user interaction, but doesn't clarify what this entails (e.g., whether it blocks execution, requires user input). It also fails to address permissions, error conditions, or mutation effects beyond the basic creation action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, straightforward sentence that gets directly to the point. While efficient, the phrase 'with interactive prompts' could be more specific to avoid ambiguity, but overall it's appropriately brief without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a creation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after creation (e.g., returns the created item, confirmation message), doesn't address authentication requirements hinted by the authToken parameter, and leaves 'interactive prompts' unexplained. Given the complexity and lack of structured data, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 4 parameters. The description adds no additional parameter information beyond what's in the schema, not even clarifying the 'interactive prompts' aspect in relation to parameters. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('create a new todo item') and resource ('todo item'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'update_todo' or 'list_todos' beyond the basic verb, and the phrase 'with interactive prompts' is somewhat vague about implementation details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'update_todo' or 'list_todos'. It doesn't mention prerequisites (e.g., authentication status), use cases, or exclusions, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete a todo item with interactive prompts
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | No | Authentication token from Kinde (optional if saved) |
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 mentions 'interactive prompts' which suggests some user interaction, but it doesn't clarify what this means operationally (e.g., confirmation dialogs, multi-step processes). It also fails to address critical aspects like whether deletion is permanent, requires specific permissions, or has side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose. It's front-loaded with the core action ('Delete a todo item') and adds a qualifying detail ('with interactive prompts'). There's no wasted verbiage or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive operation like deletion with no annotations and no output schema, the description is insufficient. It doesn't explain what 'interactive prompts' entail, what happens after deletion (e.g., confirmation message, error handling), or how this tool relates to sibling tools like 'update_todo'. More context is needed for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter with 100% coverage, so the schema fully documents the 'authToken' parameter. The description doesn't add any parameter-specific information beyond what the schema provides, which is acceptable given the high schema coverage. With only one parameter, the baseline is appropriately high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'Delete a todo item' which provides a clear verb+resource combination, but it doesn't specify what distinguishes this from the sibling 'update_todo' tool (which might also modify or remove todos). The addition of 'with interactive prompts' adds some specificity but doesn't fully differentiate from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is provided about when to use this tool versus alternatives like 'update_todo' or 'list_todos'. The description mentions 'interactive prompts' which might imply a specific context, but it doesn't state when this tool is appropriate or when other tools should be used instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Kinde billing information and subscription status
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | No | Authentication token from Kinde (optional if saved) |
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 the tool retrieves billing information and subscription status, implying a read-only operation, but doesn't clarify authentication requirements beyond what's in the schema, potential rate limits, error conditions, or what specific data is returned. This leaves significant gaps for a tool handling sensitive billing data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately front-loaded with the core functionality, though it could be slightly more structured if it included brief usage context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of billing/subscription data, no annotations, and no output schema, the description is incomplete. It doesn't explain what specific billing information is returned, how subscription status is represented, or any dependencies on other tools like 'save_token'. For a tool with sensitive financial implications, this lacks necessary detail.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'authToken' documented as optional. The description adds no additional parameter semantics beyond what the schema provides, such as token format or where it might be saved. With high schema coverage, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Get') and resource ('Kinde billing information and subscription status'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'get_subscription_status' or 'refresh_billing_status', which appear related.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'get_subscription_status' or 'refresh_billing_status'. There's no mention of prerequisites, context, or exclusions, leaving the agent to infer usage 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.
Get the user's subscription status and todo usage
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | Yes | Authentication token from Kinde |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves information, implying it's a read operation, but doesn't specify if it requires authentication (though the schema shows an authToken parameter), what permissions are needed, rate limits, or the format of the returned data. This leaves significant gaps for a tool that likely interacts with user data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that directly states the tool's purpose without any unnecessary words. It's front-loaded and efficiently conveys the core functionality, 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.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a tool that retrieves user subscription and usage data, the description is incomplete. There's no output schema, and the description doesn't explain what information is returned (e.g., subscription tier, usage limits, expiration dates). With no annotations and minimal parameter guidance beyond the schema, this leaves the agent with insufficient context to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'authToken' fully documented in the schema. The description doesn't add any meaning beyond this, such as explaining why authentication is required or how the token is used. Since the schema handles the parameter documentation adequately, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and the resource ('the user's subscription status and todo usage'), making the purpose specific and understandable. However, it doesn't explicitly distinguish this tool from sibling tools like 'get_kinde_billing' or 'refresh_billing_status', which might also relate to subscription or billing information, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. For example, it doesn't clarify if this is for checking current subscription details versus historical billing (as might be in 'get_kinde_billing') or refreshing status (as in 'refresh_billing_status'). There's no mention of prerequisites or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all todos for the authenticated user
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | No | Authentication token from Kinde (optional if saved) |
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 mentions authentication ('for the authenticated user') but doesn't specify what happens if authentication fails, whether the list is paginated, sorted, or filtered, or what the return format looks like. For a read operation with zero annotation coverage, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with zero wasted words. It's appropriately sized for a simple list operation and front-loads the core purpose effectively.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain the return format, error conditions, or behavioral details like pagination. For a tool with no structured behavioral hints, the description should provide more context to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the single parameter 'authToken' documented as optional. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline of 3 for high schema coverage without compensating value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('List all todos') and the target resource ('for the authenticated user'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'get_subscription_status' or 'get_kinde_billing' beyond the obvious domain difference, which keeps it from a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 mention prerequisites like authentication, nor does it differentiate from other todo-related tools (e.g., when to list vs. create/update/delete). This leaves the agent without contextual usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Login with Kinde to get authentication token
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only mentions the outcome ('get authentication token'). It lacks details on behavioral traits such as whether this initiates a user-facing authentication flow, requires user interaction, has rate limits, or affects session state. More context is needed for a mutation tool like login.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the key information ('Login with Kinde to get authentication token') with zero wasted words. It's appropriately sized for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of an authentication tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the authentication token is used for, how it's returned, or any prerequisites (e.g., needing Kinde credentials). More detail is needed for proper agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 documentation is needed. The description appropriately doesn't discuss parameters, earning a baseline 4 for not adding unnecessary information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Login with Kinde') and the outcome ('to get authentication token'), which is specific and unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'save_token' or 'logout', which would require a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 'save_token' (which might store tokens) or 'logout' (which might end sessions). The description only states what it does, not when it should be invoked in relation to other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Logout and clear stored authentication token
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the behavioral trait of clearing stored tokens, which is useful. However, it lacks details like whether this affects subsequent calls, if it's idempotent, or any side effects on other tools (e.g., requiring re-login).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with zero waste—it directly states the tool's action and effect. Every word earns its place, making it highly efficient and easy to understand.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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 minimal. It covers the basic purpose but lacks completeness for a mutation tool—e.g., it doesn't mention if this is a safe operation, what happens on success/failure, or how it interacts with sibling tools like 'login'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description does not add parameter details, which is appropriate, but it could slightly enhance context by explaining why no inputs are required (e.g., it uses stored state).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Logout and clear') and the resource affected ('stored authentication token'), distinguishing it from siblings like 'login' or 'save_token'. It precisely defines what the tool does without being vague or tautological.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by mentioning 'authentication token', suggesting it should be used when ending a session or revoking access. However, it does not explicitly state when to use it versus alternatives like 'login' or provide exclusions, such as whether it's safe to call repeatedly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Force refresh billing status from Kinde (useful after plan changes)
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | No | Authentication token from Kinde (optional if saved) |
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 mentions 'Force refresh' which implies a mutation or update action, but doesn't clarify if this requires specific permissions, whether it's idempotent, what side effects it has, or what the response looks like. This is inadequate for a tool that likely modifies state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action ('Force refresh billing status from Kinde') and adds a brief usage note. There's no wasted text, 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.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete. It doesn't explain what 'Force refresh' entails behaviorally (e.g., does it trigger an API call, update local cache, or something else?), what happens on success/failure, or what data is returned. For a tool with potential state changes, this leaves significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the parameter 'authToken' documented as optional. The description doesn't add any parameter-specific details beyond what the schema provides, such as format examples or authentication context. Baseline 3 is appropriate since the schema handles parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Force refresh') and resource ('billing status from Kinde'), and mentions a specific use case ('after plan changes'). However, it doesn't explicitly differentiate from sibling tools like 'get_kinde_billing' or 'get_subscription_status' in terms of when to use each, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage ('useful after plan changes') but doesn't provide explicit guidance on when to use this tool versus alternatives like 'get_kinde_billing' or 'get_subscription_status'. It also doesn't mention prerequisites or exclusions, leaving gaps in usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save your Kinde authentication token for future use
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes | Your Kinde JWT token |
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 the action ('save') but doesn't explain where tokens are stored (e.g., memory, file, session), security implications, persistence duration, or error handling. This leaves significant gaps for a tool handling authentication credentials.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with zero wasted words. It's front-loaded with the core action and resource, making it highly efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool handling authentication tokens with no annotations and no output schema, the description is insufficient. It lacks details on storage mechanism, security practices, token validation, or what 'future use' entails (e.g., which sibling tools might utilize it). This leaves critical context gaps for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the single parameter 'token' documented as 'Your Kinde JWT token.' The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline for high schema coverage without compensating value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('save') and the resource ('Kinde authentication token'), making the purpose immediately understandable. However, it doesn't differentiate this tool from potential sibling authentication tools (like 'login' or 'logout') by specifying what makes saving tokens distinct from other auth operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides minimal guidance with 'for future use,' but doesn't specify when to use this versus alternatives like 'login' (which might generate tokens) or 'refresh_billing_status' (which might use tokens). No explicit when/when-not instructions or prerequisite context about token acquisition are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing todo item with interactive prompts
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | No | Authentication token from Kinde (optional if saved) |
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 the tool updates a todo item with interactive prompts, but doesn't clarify what these prompts entail, whether the update is destructive, requires authentication, or has rate limits. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of an update tool with interactive prompts, no annotations, and no output schema, the description is incomplete. It fails to explain what the interactive prompts involve, what data is returned, or how errors are handled, leaving key contextual gaps for effective tool use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for its single parameter ('authToken'), so the description doesn't need to add parameter details. However, it doesn't provide any additional context about how parameters interact with the tool's functionality, such as how 'authToken' relates to the update process or interactive prompts.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('update') and resource ('existing todo item'), making the purpose understandable. However, it doesn't distinguish this tool from its sibling 'create_todo' or 'list_todos' in terms of scope or specific use cases, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 like 'create_todo' or 'delete_todo'. It mentions 'interactive prompts' but doesn't explain what triggers them or when this tool is preferred over direct updates, leaving usage unclear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upgrade user subscription to paid plan
| Name | Required | Description | Default |
|---|---|---|---|
| authToken | Yes | Authentication token from Kinde |
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 this is an 'upgrade' operation, implying a mutation, but doesn't describe what happens during the upgrade (e.g., billing changes, plan features, confirmation process), whether it requires specific permissions, or what the typical response includes. This is inadequate for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given this is a mutation tool (upgrading a subscription) with no annotations and no output schema, the description is incomplete. It doesn't explain what the upgrade entails, potential side effects, success/failure responses, or how it integrates with sibling tools. For a billing-related operation, more context is needed for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'authToken' fully documented in the schema as 'Authentication token from Kinde'. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline score when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('upgrade') and target resource ('user subscription to paid plan'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_subscription_status' or 'refresh_billing_status' that might be related to subscription management, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 mention prerequisites (e.g., user must have an existing free subscription), exclusions, or how it relates to sibling tools like 'get_kinde_billing' or 'refresh_billing_status'. This leaves the agent without context for proper tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The todo management tools (create_todo, delete_todo, list_todos, update_todo) are clearly distinct and cover the CRUD operations well. However, there is some ambiguity between get_kinde_billing and get_subscription_status, as both seem to retrieve subscription-related information, and refresh_billing_status overlaps with these. The authentication tools (login, logout, save_token) are distinct from the todo tools but have some functional overlap with each other.
Most tools follow a consistent verb_noun pattern (e.g., create_todo, list_todos, update_todo, get_kinde_billing, refresh_billing_status). The main deviation is 'login' and 'logout', which use a single verb without a noun, but this is a common convention for authentication actions. Overall, the naming is predictable and readable with only minor inconsistencies.
With 11 tools, the count is reasonable for a server that combines todo management with authentication and billing features. It's slightly on the higher side but not excessive, as it covers multiple domains (todos, auth, billing) within a coherent scope. The tools are well-distributed across these areas without obvious bloat.
For todo management, the server provides complete CRUD coverage (create, list, update, delete). Authentication is covered with login, logout, and token management. Billing features include status retrieval, refresh, and upgrade. A minor gap is the lack of a tool to downgrade or cancel subscriptions, but the core workflows are well-supported.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Backend for AI-built apps: database, auth, files, email, AI, payments, deploy, realtime. 170+ tools.
Managed database, auth, file storage, email, analytics, and deployment for coding agents.
Your AI builds, deploys, and runs full-stack apps on a hosted workspace created at first sign-in.
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sholajegede/todo_mcp_server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
