Look up any MCP server or AI agent. Every score shows its math.Explore →
Explorer/MCP/JesseHenson/claude_code_apex_marketplace

Spec Iterator

JesseHenson/claude_code_apex_marketplace

# Stop Building Features Based on Assumptions **Spec Iterator** conducts structured AI-powered clarification sessions that systematically uncover gaps in your requirements *before* you write code. --- ## The Problem Everyone Ignores ``` Stakeholder: "Build a dashboard for our sales team" ↓ You build it ↓ Stakeholder: "Where's the pipeline view?" ↓ You: "You didn't mention that" ↓ Stakeholder: "I assumed it was obvious" ↓ 💸 2 weeks of rework ``` **Requirements arrive incomplete.** Stakeholders don't know what they don't know. The "obvious" features only become obvious after you ship the wrong thing. --- ## How Spec Iterator Works ``` ┌─────────────────────────────────────────────────────────────┐ │ "We need order tracking for customers" │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ 🔍 ANALYZE │ │ ───────────────────────────────────────────────────────── │ │ • Entities detected: orders, customers, tracking │ │ • Gaps found: users undefined, stages unclear, no UX │ │ • Completeness: 12% │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ ❓ CLARIFY (Round 1) │ │ ───────────────────────────────────────────────────────── │ │ 1. Who are the primary users of this tracking system? │ │ 2. What order stages should be visible to customers? │ │ 3. Should users receive notifications? Which events? │ │ 4. What systems contain order data today? │ └─────────────────────────────────────────────────────────────┘ ↓ [You provide answers] ↓ ┌─────────────────────────────────────────────────────────────┐ │ ❓ CLARIFY (Round 2) — Completeness: 48% │ │ ───────────────────────────────────────────────────────── │ │ 1. Email or SMS for notifications? Or both? │ │ 2. Real-time tracking needed or periodic updates? │ │ 3. What about returns and exchanges? │ │ 4. Mobile app or web only? │ └─────────────────────────────────────────────────────────────┘ ↓ [You provide answers] ↓ ┌─────────────────────────────────────────────────────────────┐ │ ✅ READY — Completeness: 84% │ │ ───────────────────────────────────────────────────────── │ │ All critical gaps resolved. Ready to generate spec. │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ 📄 GENERATE │ │ ───────────────────────────────────────────────────────── │ │ • Problem statement with user personas │ │ • Step-by-step user flow │ │ • Features with acceptance criteria │ │ • Edge cases with handling strategies │ │ • Documented assumptions │ │ • Open questions for stakeholders │ └─────────────────────────────────────────────────────────────┘ ``` --- ## Completeness Scoring Track exactly what's missing across **5 categories**: | Category | Weight | What It Covers | |----------|--------|----------------| | **Functional** | 30% | Features, users, business rules | | **Technical** | 25% | Integrations, data, APIs | | **UX** | 20% | Flows, errors, accessibility | | **Edge Cases** | 15% | Errors, boundaries, recovery | | **Constraints** | 10% | Budget, compliance, scale | **Example output:** ``` Completeness: 73% ├── Functional: ████████░░ 85% ├── Technical: ██████░░░░ 60% ├── UX: ███████░░░ 75% ├── Edge Cases: █████░░░░░ 55% └── Constraints: ████████░░ 80% ⚠️ Technical gaps: Data refresh frequency, API rate limits ⚠️ Edge cases: Offline handling, partial order updates ``` --- ## Tools Included | Tool | Description | |------|-------------| | `spec_start_session` | Start clarification from a rough requirement | | `spec_answer_questions` | Provide answers, receive follow-up questions | | `spec_get_gaps` | See exactly what's missing and the impact | | `spec_generate` | Generate complete specification | | `spec_get_status` | Check session progress | | `spec_list_sessions` | List all active sessions | --- ## Sample Output ```markdown # Order Tracking System ## Problem Statement **Pain:** Customers have no visibility into order status after purchase **Who:** E-commerce customers, support team **Workarounds:** Calling support, checking email for shipping updates ## Features ### 1. Order Status Page (MVP) Customers can view real-time order status on a dedicated page. **Acceptance Criteria:** - [ ] Display order stages: Confirmed → Processing → Shipped → Delivered - [ ] Show estimated delivery date - [ ] Update within 5 minutes of status change - [ ] Accessible without login via order ID + email ### 2. Email Notifications (MVP) Automated emails at key order milestones. **Acceptance Criteria:** - [ ] Send on: order confirmed, shipped, out for delivery, delivered - [ ] Include tracking link when available - [ ] Unsubscribe option per notification type ## Edge Cases | Scenario | Handling | |----------|----------| | Order stuck in "Processing" > 48h | Trigger support alert | | Tracking number not yet available | Show "Tracking available soon" | | Multiple shipments per order | Show each shipment separately | ``` --- ## Who It's For **Product Managers** → Stop missing requirements that cause rework **Tech Leads** → Don't estimate incomplete requirements **Solo Developers** → Think through requirements systematically **Startup Founders** → Document ideas with implementation detail **Consultants** → Standardize discovery across clients --- ## Configuration Requires your Anthropic API key: | Parameter | Description | |-----------|-------------| | `ANTHROPIC_API_KEY` | Your Anthropic API key | **You pay Claude directly** — typical spec costs $0.05-0.15 in API usage (3-5 rounds of clarification). --- ## Quick Start 1. **Connect** Spec Iterator in Claude Desktop 2. **Run:** `spec_start_session` with your rough requirement 3. **Answer** the clarifying questions 4. **Generate** when completeness hits 80%+ --- ## Resources - **GitHub:** [Repository](https://github.com/JesseHenson/claude_code_apex_marketplace/tree/master/plugins/spec-iterator-mcp) - **Demo:** Coming soon - **Support:** Open an issue on GitHub --- ## Version **v0.1.0** — Initial release - Multi-turn clarification flow - Completeness scoring (5 categories) - Markdown and JSON output - Session persistence Site: https://aibusinessautomation.solutions/

Is this your server?

This listing has no public HTTPS endpoint we can check, so claims for it are handled by request. Tell us which RNWY account should hold it and how you are connected to the server.

Send a claim request →
0toolsUnknownlisted sinceDec 9, 2025
Checked Nov 20, 2026
RNWY's reading
The Newcomer
Hasn't been around long. Nothing caught our attention, but there isn't much history to go on yet.
Time since first listed (11mo)
The scanner shows
Not enough data to score this server yet.
Listed since Dec 9, 2025. The date Smithery gives for this listing.
Server Profile
⚙
Tools catalogued
0
No tools reported by this server.
☁
Hosting
Unknown
Hosting type not yet determined.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
—
No liveness checks recorded yet.
Publisher Verification
Not yet verified by the Official MCP Registry.
More from JesseHenson
test-mcp
Similar servers
NodeAPI
Machine-native GIS processing API for AI agents and developers. Convert, reproject, validate, repair, buffer, clip, dissolve, and tile vector geodata across 25 endpoints. Pay-per-use USDC on Solana Mainnet ($0.01/op). No accounts, no API keys. Remote MCP SSE.
astllm-mcp
An MCP server for efficient code indexing and symbol retrieval using tree-sitter AST parsing to fetch specific functions or classes without loading entire files. It significantly reduces AI token costs by providing O(1) byte-offset access to code components across multiple programming languages.
Openterms-mcp
Cryptographic proof of consent for AI agents. Sign before you act. Policy engine enforces spending caps, action whitelists, and escalation rules. Independently verifiable by anyone.
ScrubGuard
Local-first PII and secret scrubber with checksum checks and reversible LLM tokens.
Aegis-ZK
On-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute.
HiveAgent — The Agentzon
498 MCP tools across 12 industry verticals. Marketplace, escrow, DeFi, legal, healthcare, insurance, construction, and trades. USDC payments on Base L2.
Indexed from Smithery · Updates nightlyView on Smithery →