An MCP server plugin that gives AI agents a structured development lifecycle. Requirements → Design → Tasks → Implementation, with human approval gates at every transition and a real-time dashboard to manage it all.
AI coding agents are powerful, but they skip the process that makes software reliable.
Agents jump to implementation without a requirements phase, design review, or approval step. The result: rework, scope creep, and features that don’t match intent.
Without structured checkpoints, there’s no place for a human to review direction before code is written. You catch problems in PR review instead of during design.
Requirements live in chat messages that scroll away. Design decisions aren’t recorded. When the agent loses context mid-session, there’s nothing to resume from.
Every non-trivial feature follows the same path. Each transition requires explicit human approval through the dashboard. No phase-skipping.
Specs are structured markdown files that live on disk — not in any agent’s memory. They survive context loss, session boundaries, and agent switches.
A real-time web UI where you review specs, approve phase transitions, request changes, or reject proposals. The agent blocks until you decide.
Every implementation step records what was built: functions, endpoints, tests, components. The dashboard shows a complete audit trail of what shipped.
Tasks with no file overlap can execute concurrently via isolated subagents. Each task goes through implementation, compliance review, and quality review.
Product vision, technical constraints, and codebase structure captured in steering docs. Agents reference these instead of relying on chat history.
The npm package provides MCP tools and the dashboard. The GitHub repo additionally ships lifecycle skills and slash commands as plain markdown.
SpecFlow is an MCP server — any agent that speaks the protocol gets the full spec lifecycle and dashboard. Spec state lives on disk, so you can start in one agent and continue in another.
MCP server via npm + optional skills plugin. Full lifecycle skills, slash commands, and subagent dispatch.
Add as an MCP server in Gemini’s config. Full access to spec tools and the approval dashboard. Uses GEMINI.md for agent-specific behavior.
Configure in Codex’s TOML config. Same MCP tools, same workflow, same dashboard. Uses CODEX.md for agent-specific behavior.
Also verified with OpenCode. Any agent that implements MCP gets the full spec lifecycle — no vendor lock-in.
Spec documents, steering docs, and templates are stored as structured markdown. If you use Obsidian, you get graph visualization and wikilinks for free. If not, it’s just a folder of markdown files.
Each project needs a thin config file (.specflow/config.json) pointing
to your vault location. Multi-project setups share one vault.
SpecFlow handles the spec lifecycle — it doesn’t try to be a memory system, code search engine, or knowledge base. Those are separate concerns. The author’s workflow pairs SpecFlow with these companion tools, but none are required.
Indexes conversation turns into a local vector database for semantic recall across past sessions.
Semantic code search via self-hosted Milvus. Hardened fork of zilliztech/claude-context.
Cross-session memory for retro lessons, decisions, and handoffs. Cloud API (self-hosted fork planned).
These integrations are part of the author’s workflow — not SpecFlow requirements. The MCP server and dashboard work standalone with just Node.js.
One line to install the MCP server. Copy skills from the repo for the full workflow.
Requires Node.js 18+. Works with any MCP-compatible agent.
SpecFlow is open source, in active development, and used daily by the author across multiple projects. It’s a work in progress — contributions, issues, and feedback are welcome.