Spec-driven Development MCP Server
The Spec-driven Development MCP Server provides an AI-guided, structured workflow for complete software development from concept to execution.
Core Workflow Capabilities:
Start & Define: Initiate development workflows (
spec_driven_dev_workflow_start) and confirm feature goals with specific names and summariesRequirements Gathering: Collect and confirm detailed requirements in EARS format using
spec_driven_dev_requirements_startandspec_driven_dev_requirements_confirmedTechnical Design: Create and confirm comprehensive design documentation covering architecture, components, and data models
Task Planning: Break down features into executable, manageable tasks with confirmation workflows
Execution: Systematically guide task implementation with
spec_driven_dev_execute_start, optionally targeting specific tasks
Documentation & Organization:
Generates structured outputs (
requirements.md,design.md,tasks.md) in feature-specific directoriesCreates organized project documentation throughout the development lifecycle
Integration:
Compatible with AI-powered IDEs like Cursor and Claude Desktop
Supports JSON configuration for seamless setup and interactive development experience
Mentioned in the context of OAuth login options for the user authentication feature example
Provides OAuth authentication integration as demonstrated in the example authentication workflow
Serves as the runtime environment for the MCP server, with version 18+ required for development
Provides package installation and management for the MCP server
Recommended as the preferred package manager for development of the MCP server
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., "@Spec-driven Development MCP Serverhelp me build a user authentication feature"
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.
Spec-driven Development Workflow
An AI-guided spec-driven development workflow available as both a Claude Code Skill and MCP Server. Transform your development process with structured, step-by-step guidance from idea to implementation.
What is Spec-driven Development?
Spec-driven development is a methodology that emphasizes creating detailed specifications before writing code. This approach helps ensure clear requirements, better design decisions, and more maintainable code. This workflow guides you through the process with AI assistance.
Related MCP server: Interactive Feedback MCP
π― Two Ways to Use This Workflow
Option 1: Claude Code Skill (Recommended for Claude Code Users)
Simple, integrated, no setup required!
The workflow is available as a native Claude Code Skill. Just invoke it in any conversation:
/spec-codingOr naturally:
I want to use the spec-coding workflow to build [feature]Benefits:
β No installation or configuration needed
β Native integration with Claude Code
β Seamless conversation flow
β Automatic progress tracking with TodoWrite
Learn more: Skill Documentation | Migration Guide
Option 2: MCP Server (For Other IDEs)
Use as an MCP server for Claude Desktop, Cursor, or other MCP-compatible tools.
Installation via Smithery:
npx -y @smithery/cli install @kevinlin/spec-coding-mcp --client claudeLearn more: See MCP Server Setup below.
Features
Complete Development Workflow: From goal collection to task execution
AI-Powered Guidance: Step-by-step instructions for each development phase
Structured Documentation: Generates organized specs in EARS format
Template-Based: Uses proven templates for requirements, design, and tasks
MCP Server Setup
This section is for users who want to use the workflow as an MCP server (Option 2 above).
Installation
Installing via Smithery
To install spec-coding-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @kevinlin/spec-coding-mcp --client claudeUsing npx (Recommended)
# Always get the latest version
npx spec-coding-mcp@latest
# Or simply (will also get latest)
npx spec-coding-mcpUsing npm
npm install -g spec-coding-mcp
spec-coding-mcpUsage
With Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"spec-coding-mcp": {
"command": "npx",
"args": ["spec-coding-mcp@latest"],
"env": {},
"disabled": false
}
}
}Available Tools
spec_coding_workflow_start - Start the development workflow
spec_coding_goal_confirmed - Confirm feature goals
spec_coding_requirements_start - Begin requirements gathering
spec_coding_requirements_confirmed - Confirm requirements completion
spec_coding_design_start - Start design documentation
spec_coding_design_confirmed - Confirm design completion
spec_coding_tasks_start - Begin task planning
spec_coding_tasks_confirmed - Confirm task planning completion
spec_coding_execute_start - Start task execution
Workflow Stages & Example
The spec-driven development process follows five distinct stages. Here's how it works with a real example - building a user authentication feature:
1. Goal Collection - Define What You Want to Build
Purpose: Establish clear, specific objectives for your feature.
Example Interaction:
User: I want to build a user authentication feature
Assistant: Let me start the spec-driven development workflow for you.
[calls spec_coding_workflow_start]
Let's define your feature goals:
1. What specific authentication methods do you want to support?
2. Do you need social login (Google, GitHub, etc.)?
3. What user roles and permissions are required?
User: I need email/password login with JWT tokens, plus Google OAuth, and basic user/admin roles.
Assistant: Perfect! Let me confirm:
- Feature: User authentication system
- Methods: Email/password + Google OAuth
- Tokens: JWT-based
- Roles: User and Admin
- Feature name: "user-authentication"
Is this correct?
User: Yes, that's exactly what I need.
[calls spec_coding_goal_confirmed with feature_name="user-authentication"]2. Requirements Gathering - Create Detailed EARS-format Requirements
Purpose: Transform your goals into specific, testable requirements using the EARS (Easy Approach to Requirements Syntax) format.
Example Interaction:
Assistant: Great! Now let's gather detailed requirements.
[calls spec_coding_requirements_start]
[Assistant generates detailed EARS-format requirements in docs/specs/user-authentication/requirements.md]
- WHEN a user provides valid email/password THEN the system SHALL authenticate them
- GIVEN a user wants Google OAuth WHEN they click "Sign in with Google" THEN the system SHALL redirect to Google
- WHERE user roles are needed IF user is admin THEN they SHALL access admin features
User: The requirements look comprehensive. Approved!
[calls spec_coding_requirements_confirmed]3. Design Documentation - Technical Architecture and Design
Purpose: Create detailed technical specifications including architecture, component design, data models, and API specifications.
Example Interaction:
Assistant: Now let's create the technical design.
[calls spec_coding_design_start]
[Assistant creates detailed design document including:]
- Database schema for users, sessions, oauth_tokens
- Authentication middleware architecture
- JWT token structure and validation flow
- Google OAuth integration endpoints
- Role-based access control implementation
User: Design looks good, proceed!
[calls spec_coding_design_confirmed]4. Task Planning - Break Down into Executable Tasks
Purpose: Decompose the feature into specific, prioritized development tasks with clear dependencies.
Example Interaction:
Assistant: Let's break this down into executable tasks.
[calls spec_coding_tasks_start]
[Assistant creates numbered task list:]
1. Set up database models (User, Session, OAuthToken)
2. Implement JWT token service
3. Create email/password authentication endpoints
4. Integrate Google OAuth flow
5. Build role-based middleware
6. Add frontend login/register forms
7. Write integration tests
User: Task breakdown is perfect!
[calls spec_coding_tasks_confirmed]5. Task Execution - Implement the Code
Purpose: Execute the planned tasks systematically, implementing the feature according to specifications.
Example Interaction:
Assistant: Time to implement! Let's start coding.
[calls spec_coding_execute_start]
[Assistant implements each task step by step:]
- Creates User model with email, password_hash, role fields
- Builds JWT service with sign/verify methods
- Implements /auth/login and /auth/register endpoints
- Integrates Google OAuth with Passport.js
- Creates role-checking middleware
- Builds React login/register components
- Writes comprehensive test suiteGenerated Project Structure
Throughout the workflow, the following documentation structure is created:
docs/specs/{feature_name}/
βββ requirements.md # EARS-format requirements
βββ design.md # Technical architecture
βββ tasks.md # Implementation checklistDevelopment
Prerequisites
Make sure you have Node.js 18+ installed.
Setup
# Install dependencies with pnpm (recommended)
pnpm install
# Or with npm
npm installRunning the Project
# Development mode with pnpm
pnpm dev
# Or with npm
npm run dev
# Build with pnpm
pnpm build
# Or with npm
npm run build
# Start built version with pnpm
pnpm start
# Or with npm
npm start
# Test with pnpm (when available)
pnpm test
# Or with npm
npm testPublishing
To publish the package to npm:
# Build the project
pnpm build
# Publish to npm (will automatically run prepublishOnly script)
npm publishContributing & License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT
Attribution
This project was inspired by and builds upon concepts from vibedevtools by @yinwm, a collection of development efficiency tools.
Available Tools
9 toolsspec_coding_design_confirmedC
Confirm the completion of the design document and proceed to the task planning phase
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It mentions 'confirm' and 'proceed', suggesting a state transition or workflow step, but does not clarify if this is a read-only check, a mutation that updates status, what happens on failure, or any side effects. 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 action. It is front-loaded with the core purpose and avoids unnecessary details, though it could be slightly more informative without losing conciseness.
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 workflow tool with no annotations and no output schema, the description is incomplete. It lacks details on what 'confirmation' entails, the expected outcome, error handling, or how it integrates with sibling tools, making it inadequate for an agent to use effectively without additional context.
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 both parameters ('session_id' and 'feature_name') documented in the schema. The description adds no additional meaning or context about the parameters beyond what the schema provides, such as how they relate to the confirmation process. 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 states a purpose ('Confirm the completion of the design document and proceed to the task planning phase'), which is clear but vague. It uses a verb ('Confirm') and resource ('design document'), but does not specify what 'confirm' entails or how it differs from sibling tools like 'spec_coding_design_start' or 'spec_coding_tasks_confirmed', making it less specific.
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 after design document completion and before task planning, but provides no explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or comparisons to sibling tools, leaving the agent to infer context without clear direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_design_startC
Start the design documentation phase and provide guidance for creating design documents
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name |
TDQS
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. While 'Start' implies an initiation action, it doesn't describe what 'starting' entails (e.g., creates a new document, updates a status, triggers notifications), what permissions are needed, or what happens if the phase is already started. This leaves significant behavioral gaps.
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 with the core action.
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 for a tool that initiates a phase and provides guidance. It doesn't explain what 'guidance' entails (e.g., format, content, or examples of design documents), what the expected outcome is, or how it fits into the broader workflow with sibling tools.
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 already documents both parameters (session_id and feature_name) adequately. The description adds no additional meaning about these parameters beyond what's in the schema, such as how they relate to the design phase or guidance provided.
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 ('Start') and resource ('design documentation phase'), and indicates it provides guidance for creating design documents. However, it doesn't explicitly differentiate from sibling tools like 'spec_coding_workflow_start' or 'spec_coding_tasks_start' that might also initiate phases.
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. With multiple sibling tools that appear to be part of a workflow (e.g., 'spec_coding_requirements_start', 'spec_coding_tasks_start'), there's no indication of sequencing, prerequisites, or exclusions for this design phase initiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_execute_startC
Start the task execution phase and provide guidance for task execution
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name | |
| task_id | No | Optional: Specify the task ID to execute; if not specified, the next unfinished task will be executed |
TDQS
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 mentions 'start the task execution phase' and 'provide guidance,' but fails to specify what 'guidance' entails (e.g., instructions, prompts, or status updates), whether this is a read-only or mutative operation, potential side effects, or any constraints like rate limits. This leaves key behavioral traits undefined, making it inadequate for a tool with no annotation support.
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 concise with a single sentence that front-loads the core action ('Start the task execution phase') and adds a secondary function ('provide guidance for task execution'). It avoids unnecessary words, but could be more structured by clarifying the relationship between starting and providing guidance. Overall, it is efficiently sized, though slightly vague.
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 implied by sibling tools in a workflow context, no annotations, and no output schema, the description is incomplete. It lacks details on what 'guidance' includes, the expected outcome, error conditions, or how it fits into the broader workflow (e.g., after which sibling tools it should be used). This makes it insufficient for an agent to understand the tool's role and behavior fully.
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 clear documentation for all three parameters. The description adds no additional meaning beyond the schema, as it does not explain parameter roles, interactions, or implications (e.g., how 'session_id' and 'feature_name' relate to starting execution). Since schema coverage is high, the baseline score of 3 is appropriate, as the description does not compensate but also does not detract from the schema's 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 states the tool 'Start[s] the task execution phase and provide[s] guidance for task execution,' which gives a vague purpose. It mentions 'task execution phase' and 'guidance,' but lacks specificity about what resource is being acted upon (e.g., a session, feature, or task) and how it differs from sibling tools like 'spec_coding_tasks_start' or 'spec_coding_workflow_start.' This makes it unclear if it initiates execution, provides instructions, or both, without clear distinction from related tools.
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. With sibling tools like 'spec_coding_tasks_start' and 'spec_coding_workflow_start,' there is no indication of context, prerequisites, or exclusions. The input schema hints at usage through optional parameters (e.g., 'task_id' for specifying a task), but the description itself offers no explicit when-to-use or when-not-to-use instructions, leaving usage ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_goal_confirmedB
Confirm the completion of the feature goal, set the feature_name, and proceed to the requirements collection phase
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name generated based on the goal (e.g., user-auth) | |
| goal_summary | Yes | Brief description of the feature goal |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but offers minimal behavioral insight. It mentions state transitions ('proceed to the requirements collection phase') but doesn't disclose whether this tool triggers side effects, requires specific permissions, affects session state, or has error conditions. For a tool with 3 required parameters and no annotation coverage, this is inadequate.
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 with zero wasted words. It's appropriately sized for the tool's apparent complexity and front-loads the key actions (confirm, set, proceed). Every element serves a purpose.
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 3 required parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what 'confirmation' entails, what happens if confirmation fails, what the tool returns, or how it interacts with the broader workflow system. The description assumes context that isn't documented.
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%, providing good parameter documentation. The description adds no specific parameter semantics beyond what's in the schema (session_id, feature_name, goal_summary). It mentions 'set the feature_name' which aligns with the schema but doesn't provide additional context about parameter relationships or usage.
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 specific verbs ('Confirm the completion', 'set', 'proceed to') and identifies the resource ('feature goal'). It distinguishes from some siblings by focusing on goal confirmation rather than design or requirements phases, though it doesn't explicitly differentiate from all workflow-related tools.
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 'proceed to the requirements collection phase', suggesting this tool is used after goal completion and before requirements gathering. However, it doesn't provide explicit when-to-use guidance, alternatives, or exclusions compared to other sibling tools like spec_coding_workflow_start.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_requirements_confirmedC
Confirm the completion of requirements collection and proceed to the design phase
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It implies a state transition ('proceed to the design phase') but doesn't disclose behavioral traits like whether this is a read-only or mutating operation, what happens if requirements aren't complete, if it requires specific permissions, or what the response looks like. For a tool with no annotations, this leaves critical gaps in understanding its 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 states the tool's action concisely. It's front-loaded with the main purpose, though it could be more structured by explicitly mentioning parameters or context. There's no wasted text, earning it a high score for brevity.
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 complexity (involving phase transitions in a workflow), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'confirming' entails, what 'proceed' does, or the expected outcome. For a tool with 2 parameters and siblings indicating a multi-step process, more detail is needed to guide proper 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 both parameters (session_id and feature_name) documented in the schema. The description adds no meaning beyond what the schema providesβit doesn't explain how these parameters relate to confirming requirements or proceeding to design. Baseline is 3 since the schema does the heavy lifting, but no extra value is added.
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's purpose as confirming requirements collection completion and proceeding to design phase, which is clear but vague. It uses the verb 'confirm' and mentions 'requirements collection' and 'design phase', but doesn't specify what resource or system this applies to, nor does it distinguish from sibling tools like 'spec_coding_requirements_start' or 'spec_coding_design_start'.
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., after requirements collection is done), exclusions, or how it differs from siblings such as 'spec_coding_requirements_start' (which might start requirements) or 'spec_coding_design_confirmed' (which confirms design). Without this, users must infer usage from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_requirements_startC
Start the requirements collection phase and provide guidance for requirements gathering
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name |
TDQS
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 mentions 'start' and 'provide guidance', implying an initiating action, but doesn't disclose behavioral traits such as whether this is a read-only or mutating operation, what 'guidance' entails (e.g., textual output, structured data), or any side effects. The description is minimal and lacks essential context for safe invocation.
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 states the core action and outcome without unnecessary words. It's appropriately sized for a simple tool, though it could be more front-loaded with key details. There's no waste, but it might benefit from slightly more structure to enhance clarity.
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 complexity (initiating a phase with guidance), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'guidance' means, the format of output, or how this fits into the broader workflow with siblings. For a tool that likely returns instructional content, more detail is needed to guide the agent 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 input schema has 100% description coverage, with parameters 'session_id' and 'feature_name' clearly documented. The description adds no meaning beyond the schemaβit doesn't explain how these parameters influence the requirements collection or guidance. Given high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.
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 'Start[s] the requirements collection phase and provide[s] guidance for requirements gathering', which indicates a general purpose but lacks specificity. It mentions 'requirements collection phase' and 'requirements gathering', but doesn't clarify what resource or system this applies to, nor how it distinguishes from siblings like 'spec_coding_design_start' or 'spec_coding_tasks_start'. The purpose is vague rather than 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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context (e.g., when in a workflow), or exclusions. With siblings like 'spec_coding_requirements_confirmed' and 'spec_coding_design_start', there's no indication of sequencing or differentiation, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_tasks_confirmedC
Confirm the completion of task planning and proceed to the execution phase
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name |
TDQS
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 confirming completion and proceeding to execution, but lacks details on what this entailsβe.g., whether it triggers side effects, requires specific permissions, or changes system state. This leaves key behavioral traits unspecified for a tool that seems to involve workflow transitions.
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 action. It's front-loaded with the core purpose, though it could be more structured by including brief context. There's no wasted text, making it appropriately concise for its content.
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 workflow transition tool with no annotations and no output schema, the description is incomplete. It fails to explain what 'confirming completion' entails, what happens after proceeding to execution, or any potential outcomes. This leaves significant gaps in understanding the tool's role and effects within the sibling toolset.
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 parameters 'session_id' and 'feature_name' clearly documented. The description adds no additional meaning beyond the schema, such as explaining how these parameters relate to the confirmation process. Since schema coverage is high, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.
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 action ('Confirm the completion of task planning and proceed to the execution phase'), which is clear but vague. It doesn't specify what resource or system this applies to, nor does it differentiate from sibling tools like 'spec_coding_tasks_start' or 'spec_coding_execute_start', leaving the exact purpose ambiguous.
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 on when to use this tool versus alternatives. The description implies it's for transitioning from planning to execution, but it doesn't specify prerequisites, exclusions, or how it relates to siblings such as 'spec_coding_design_confirmed' or 'spec_coding_goal_confirmed', offering minimal usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_tasks_startC
Start the task planning phase and provide guidance for creating the task list
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | Session identifier | |
| feature_name | Yes | Feature name |
TDQS
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 mentions starting a phase and providing guidance, but doesn't clarify what 'guidance' entails (e.g., structured output, prompts, or instructions), whether this initiates a state change, or any side effects like authentication needs or rate limits. This is inadequate for a tool with no 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 front-loads the key action and outcome without unnecessary words. It could be slightly more structured by explicitly mentioning the workflow context, but it earns its place by being direct and clear.
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 implied by sibling tools in a multi-phase workflow, no annotations, and no output schema, the description is incomplete. It doesn't explain what 'guidance' looks like, how this tool interacts with others (e.g., 'spec_coding_tasks_confirmed'), or the expected behavior, leaving significant gaps for an agent to operate 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 both parameters ('session_id' and 'feature_name') clearly documented in the schema. The description adds no additional meaning about these parameters beyond what the schema provides, such as format examples or contextual usage, so it meets the baseline of 3 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 ('Start the task planning phase') and the outcome ('provide guidance for creating the task list'), which gives a specific verb+resource combination. However, it doesn't explicitly distinguish this tool from its siblings like 'spec_coding_design_start' or 'spec_coding_workflow_start', which likely handle different phases of the same workflow.
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., whether other tools must be called first), exclusions, or how it fits into the broader workflow with its siblings, leaving the agent to guess based on naming conventions alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
spec_coding_workflow_startB
Start the specs workflow and begin the goal collection phase
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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 mentions starting a workflow and beginning a phase, but lacks details on behavioral traits such as side effects, permissions needed, whether it's idempotent, or what happens upon invocation. This is inadequate for a 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 unnecessary words. It is front-loaded and every part contributes to understanding the action and phase.
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 what the tool returns, what 'starting' entails behaviorally, or how it fits into the broader workflow with sibling tools. For a tool in a complex sibling set, 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?
The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate, earning a baseline score of 4 for tools with no parameters.
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 ('Start') and the target ('specs workflow'), and specifies the initial phase ('goal collection phase'). It distinguishes this as the beginning of a workflow rather than other phases, though it doesn't explicitly differentiate from sibling tools like 'spec_coding_design_start' or 'spec_coding_requirements_start'.
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 this is the first step in a workflow ('Start'), but provides no explicit guidance on when to use it versus alternatives, prerequisites, or exclusions. It doesn't reference sibling tools or context for selection, leaving usage unclear beyond the implied initiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
18 tool updates
v1.0.0- Added
spec_coding_design_confirmed - Added
spec_coding_design_start - Added
spec_coding_execute_start - Added
spec_coding_goal_confirmed - Added
spec_coding_requirements_confirmed - Added
spec_coding_requirements_start - Added
spec_coding_tasks_confirmed - Added
spec_coding_tasks_start - Added
spec_coding_workflow_start - Removed
spec_driven_dev_design_confirmed - Removed
spec_driven_dev_design_start - Removed
spec_driven_dev_execute_start - Removed
spec_driven_dev_goal_confirmed - Removed
spec_driven_dev_requirements_confirmed - Removed
spec_driven_dev_requirements_start - Removed
spec_driven_dev_tasks_confirmed - Removed
spec_driven_dev_tasks_start - Removed
spec_driven_dev_workflow_start
9 tool updates
- First observed
spec_driven_dev_design_confirmed - First observed
spec_driven_dev_design_start - First observed
spec_driven_dev_execute_start - First observed
spec_driven_dev_goal_confirmed - First observed
spec_driven_dev_requirements_confirmed - First observed
spec_driven_dev_requirements_start - First observed
spec_driven_dev_tasks_confirmed - First observed
spec_driven_dev_tasks_start - First observed
spec_driven_dev_workflow_start
TDQS
Every tool has a clearly distinct purpose corresponding to a specific phase in the spec-driven development workflow. The naming convention with phase names (goal, requirements, design, tasks, execute) and action suffixes (_start, _confirmed) eliminates any ambiguity about which tool to use for which workflow step.
All tools follow an identical pattern: 'spec_coding_' + [phase_name] + '_' + [action]. This consistent snake_case structure with predictable verb endings (_start, _confirmed) creates excellent predictability and readability across the entire tool set.
With 9 tools, this server perfectly covers the complete spec-driven development lifecycle from workflow initiation through execution. Each tool represents a distinct phase transition, making the count well-scoped and appropriate for managing this structured development process.
The tool set provides complete coverage of the spec-driven development workflow, including all phase transitions from workflow start through execution. There are no gaps - every phase has both a start and confirmed tool, creating a complete, linear progression without dead ends for agents to follow.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Official DevSpeak MCP server β translate technical text into formal specs from any AI IDE or agent
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
Related MCP Servers
- AlicenseDqualityDmaintenanceAn MCP server that implements a structured workflow for LLM-based coding, guiding development through feature clarification, documentation generation, phased implementation, and progress tracking.106718MIT
- AlicenseAqualityDmaintenanceA MCP server that enables human-in-the-loop workflow in AI-assisted development tools by allowing users to run commands, view their output, and provide textual feedback directly to the AI assistant.11,711MIT
- FlicenseAqualityDmaintenanceAn MCP server that automates the full software development lifecycle through an AI-driven TDD state machine. It handles everything from task decomposition and test-driven development to integration testing and automated pull request creation.4-
- AlicenseAqualityBmaintenanceMCP server that integrates DevFlow with AI code assistants to enforce structured development workflows including planning, task tracking, and code review gates.652471MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/kevinlin/spec-coding-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server