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., "@agentic-fy propose a dark mode 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.
A performant, lean TypeScript CLI for spec-driven workflows, with MCP support.
agentic-fy structures the spec-driven development cycle — from draft to archive — and exposes that flow both in the terminal and as an MCP server, so an AI agent can drive the work inside your IDE.
Lean. Few dependencies, no ceremony. Easy to understand and extend.
MCP-first. Integrates with the IDE via the Model Context Protocol, not via per-tool skill files.
Spec-driven. Every change starts from clear artifacts: proposal, design, tasks, and spec.
Related MCP server: AiDD MCP Server
Node.js >= 20.19.0
npm install -g agentic-fyOr run without installing:
npx agentic-fy --versioncd your-project
agentic-fy init # creates the structure and integrates your IDE (MCP)
agentic-fy explore # (optional) think before coding
agentic-fy propose "dark mode" # drafts proposal, design, tasks, and spec
agentic-fy apply # tracks the tasks
agentic-fy verify # checks whether it's ready
agentic-fy archive # archives the completed changeinit createsagentic-fy.config.yaml # project configuration
agentic-fy/
├── specs/ # project specs
├── changes/ # proposed changes (one folder per change)
│ └── archive/ # completed changesinit is idempotent and also configures the MCP integration for your IDE. In the terminal it asks which tool to configure; to skip the prompt use --tools:
agentic-fy init --tools kiro,cursor # configures the chosen tools
agentic-fy init --tools none # only the base structureThe mcp.json merge is non-destructive: if you already have one, agentic-fy only adds its own server without deleting the rest.
Command | What it does |
| Creates the base structure and integrates the AI tools (MCP) |
| Thinking mode: maps the problem and lists active changes |
| Creates the change and drafts |
| Reads |
| Checks artifacts and tasks, and runs each requirement's evidence command; marks as |
| Applies the change's spec deltas to the project specs, keeping the change active (early-sync) |
| Applies the spec deltas to the project specs, then archives the change |
| Lists changes (or specs) |
| Shows a change, an artifact, or a spec |
| Validates the artifacts of a change |
| Overview of changes by stage, progress, and issues |
| Reads and edits |
| Checks project integrity |
| Gathers config, changes, and specs into a brief for the agent |
| Specs and changes dashboard (interactive in the terminal) |
| Prints an autocompletion script (powershell/bash/zsh) |
| Starts the MCP server (stdio) |
Full reference in docs/commands.md.
When you run propose, the change gets:
Artifact | Purpose |
| The "why" and the "what" — intent, scope, and approach |
| Requirements and acceptance criteria |
| The "how" — technical approach and decisions |
| Implementation checklist |
If you chose a tool during init, your IDE's mcp.json has already been configured — just reload the IDE. To start the server manually:
agentic-fy mcpIt exposes the explore, propose, apply, verify, merge, archive, list, show, validate, status, and context tools to any MCP-compatible agent. Per-editor configuration details in docs/commands.md.
npm install
npm run build # compiles TypeScript to dist/
npm run dev # tsc in watch mode
npm test # runs the suite (vitest)
node bin/agentic-fy.js --versionMIT
This server cannot be deployed
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent
Git-backed platform for skills, tools, and context for AI agents
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
Manage SysML2 projects and files directly through your coding agent.
