spec-builder-mcp
The spec-builder-mcp server helps AI assistants plan and document software features using a structured Software Design Document (SDD) approach, storing documents locally in a .docs/features/ directory.
List features (
spec_list): Retrieve all documented features in the workspace.Search features (
spec_search): Search feature names and document contents to find existing features.Create feature (
spec_create): Create a new feature folder (auto-prefixed withFEAT-) withrequirements.mdandtechnical_design.mdinitialized from templates.Update document (
spec_update): Write or overwrite markdown content to an existing feature'srequirements.mdortechnical_design.md.Delete feature (
spec_delete): Permanently remove a feature folder and all its documents.Guided workflow (
spec_wizardprompt): An AI-driven assistant that iteratively walks through requirements gathering and technical design.
All operations require a workspace_path (absolute path to your project), and feature-specific operations reference the feature name without the FEAT- prefix.
Click on "Deploy 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-builder-mcp Create a new feature for user profile editing"
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-builder-mcp
An MCP (Model Context Protocol) server that helps AI assistants plan and document software features using a structured Software Design Document (SDD) approach.
Instead of jumping straight into code, the AI guides you through creating proper documentation — requirements and technical design — before any implementation begins.
How it works
When connected to an MCP-compatible client (e.g. Claude Desktop, Cursor, Junie), the server exposes tools and a workflow prompt that the AI uses to manage feature documentation in your project.
All documents are stored locally in your project under .docs/features/:
your-project/
└── .docs/
└── features/
└── user-login/
├── requirements.md
└── technical_design.mdWorkflow
You trigger the
spec_wizardprompt in your MCP client.The AI asks: "What do you want to build?" — or skip this step by passing a file (e.g.
@ticket.json,@brief.md), which the AI uses as the basis for the spec.It searches existing feature docs to check if the feature already exists.
If it's new, it creates the feature folder with both documents initialised from the built-in templates.
Both documents are filled out iteratively (requirements first, then technical design) and saved with
spec_update.
Related MCP server: Vibe Coder MCP
Tools
Tool | Description |
| Lists all documented features in |
| Searches feature names and document contents for a query |
| Creates a new feature folder ( |
| Writes content to an existing feature's |
| Permanently deletes a feature folder and all its documents |
Example
An example specification generated with this tool is included in this repository:
FEAT-spec-wizard/
├── requirements.md # functional & non-functional requirements for the Spec Wizard itself
└── technical_design.md # architecture, components, and tool interaction flowSetup
1. Build
npm install
npm run build2. Configure your MCP client
Add the server to your MCP client configuration:
{
"mcpServers": {
"spec-builder-mcp": {
"command": "node",
"args": ["/absolute/path/to/spec-builder-mcp/build/index.js"]
}
}
}3. Use
In your MCP client, select the spec_wizard prompt to begin a guided feature planning session.
Development
npm run build # compile TypeScript + copy prompt files
npm start # run the built serverSource structure:
src/
├── index.ts # entry point — registers tools and prompt
├── helpers/
│ └── directory.helper.ts # resolves .docs/features/ path
├── prompts/
│ ├── sdd-workflow.prompt.json # prompt metadata
│ └── sdd-workflow.prompt.md # prompt content sent to the AI
├── templates/
│ ├── requirements.md # template for requirements documents
│ └── technical_design.md # template for technical design documents
└── tools/
├── list-features.tool.ts
├── search-feature.tool.ts
├── create-feature.tool.ts
├── update-feature.tool.ts
└── delete-feature.tool.tsAvailable Tools
5 toolsspec_createA
Creates a new feature folder (prefixed with FEAT-) and initializes both requirements.md and technical_design.md.
Inputs: feature_name (required), workspace_path (required).
spec_deleteA
Permanently deletes a feature folder and all its documents.
Inputs: feature_name (required), workspace_path (required).
spec_listB
Lists all documented features in the .docs/features directory of the workspace.
Inputs: workspace_path (required).
spec_searchA
Searches existing feature documentation for a specific query to see if a feature already exists.
Inputs: query (required), workspace_path (required).
spec_updateB
Writes content to a document (requirements or technical_design) of an existing feature.
Inputs: type (required), content (required), feature_name (required), workspace_path (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation (create, delete, list, search, update) with no overlap, ensuring an agent can clearly differentiate them.
All tools follow a consistent 'spec_verb' pattern using snake_case, making naming predictable and easy to understand.
With 5 tools, the set is well-scoped for managing feature specifications, covering essential operations without unnecessary bloat.
CRUD-like operations are present except for a dedicated read/get tool to retrieve the full content of a single feature, which is a notable gap.
Related MCP Connectors
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
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.1069 npm17MIT
- AlicenseBqualityDmaintenanceAn MCP server that supercharges AI assistants with powerful tools for software development, enabling research, planning, code generation, and project scaffolding through natural language interaction.1169 npm102MIT
- AlicenseCqualityBmaintenanceAn MCP server implementing Spec-Driven Development workflows for AI-agent CLIs and IDEs like Claude Code and Cursor, enabling spec-first development with automated workflow guidance and quality checks.1783 npm54MIT
- FlicenseAqualityDmaintenanceAn MCP server that provides AI clients with access to developer documentation via llms.txt files. Exposes tools, resources, and prompts.31-