Spec Kit MCP Server
Provides tools for interacting with Spec Kit templates and workflows to manage project specifications, planning, and implementation using GitHub's spec-kit framework.
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 Kit MCP Serverhelp me create a constitution for our new API project"
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 Kit MCP Server
This is a Model Context Protocol (MCP) server for Spec Kit. It allows AI assistants to interact with Spec Kit templates and workflows directly to help manage project specifications, planning, and implementation.
Prerequisites
Before using this MCP server, you must have specify-cli installed on your system.
Persistent Installation (Recommended)
Install once and use everywhere:
uv tool install specify-cli --from git+https://github.com/github/spec-kit.gitThen use the tool directly:
specify init <PROJECT_NAME>
specify checkTo upgrade Specify, see the Upgrade Guide for detailed instructions. Quick upgrade:
uv tool install specify-cli --force --from git+https://github.com/github/spec-kit.gitRelated MCP server: Foundry MCP
Installation & Usage
Using with MCP Clients (e.g., Claude Desktop, Cursor)
You can run this server directly using npx. Add the following configuration to your MCP client settings:
{
"mcpServers": {
"spec-kit": {
"command": "npx",
"args": [
"-y",
"@anyicode/spec-kit-mcp@latest"
]
}
}
}Features
This server provides prompts and tools to guide the AI through the Spec Kit workflow:
Constitution (
speckit.constitution): Establish or review project principles (code quality, testing, etc.).Specify (
speckit.specify): Combine templates with user requirements to describe what to build.Plan (
speckit.plan): Analyze the project and create a technical plan.Tasks (
speckit.tasks): Break down the plan into actionable tasks.Implement (
speckit.implement): Provide implementation guidelines.
The server automatically detects and uses the commands/ directory in your project root to access these templates.
Publishing
To release a new version of this package, follow these steps:
Update the package version (e.g., patch, minor, major):
npm version patchBuild the project:
npm run buildPublish the package to npm:
npm publish --access publicVerify the package is published:
npm view @anyicode/spec-kit-mcp
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 Servers
- AlicenseBqualityDmaintenanceEnables AI-guided spec-driven development workflow that transforms ideas into implementation through structured stages: goal collection, requirements gathering in EARS format, technical design documentation, task planning, and systematic code execution.Last updated91621MIT
- Alicense-qualityCmaintenanceEnables spec-driven development workflows with AI assistants, providing tools for managing specification lifecycles, task dependencies, code navigation, testing, and automated reviews through a unified CLI and MCP interface.Last updated4MIT
- Alicense-qualityCmaintenanceConnects OpenSpec specification system to AI coding assistants, enabling automated spec-driven development workflows.Last updated542MIT

SpecDown MCP Serverofficial
Alicense-qualityCmaintenanceGives AI assistants direct read/write access to SpecDown Markdown spec documents, enabling spec-driven development without copy-pasting.Last updated213MIT
Related MCP Connectors
Design spec + milestones AI coding agents read before building; drift flagged, changes reviewed.
Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
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/anyiba/spec-kit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server