fast_award_screener_mcp

DK Elite AI Solutions — DIBBS Fast Award Screener

Screens DIBBS RFQs for micro-purchase viability against your Net30 + sub-$1K + 1–2 business day threshold. Zero LLM calls in the pipeline — pure deterministic logic.

---

Architecture

screen_rfq / screen_rfq_batch
        │
        ▼
┌─────────────────────────────────────┐
│  Node 1: parse_rfq                  │  ← PDF fetch + regex extraction
│  Node 2: check_flags                │  ← QPL/Berry/CMMC/ITAR/CAI/HAZMAT
│  Node 3: score_opportunity          │  ← 0–100 score across 5 dimensions
│  Node 4: lookup_grainger            │  ← Price + margin (skipped if disq'd)
└─────────────────────────────────────┘
        │
        ▼
   HITL Summary → Zapier → Gmail/Slack → You approve → DIBBS Fast Trak

---

Tools

Tool	Description
screen_rfq	Full pipeline for one RFQ
screen_rfq_batch	Parallel screen up to 10 RFQs, ranked by score
explain_flags	Reference: what each disqualifying flag means

---

Installation

cd fast_award_screener_mcp
pip install -r requirements.txt
python -m py_compile server.py && echo "✅ Syntax OK"

---

Claude Desktop Config

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "fast_award_screener": {
      "command": "python",
      "args": ["/path/to/fast_award_screener_mcp/server.py"],
      "env": {}
    }
  }
}

---

Zapier Integration (HTTP mode)

python server.py --transport streamable_http --port 8001
# Then expose via ngrok:
ngrok http 8001

Zapier webhook → POST to ngrok URL → tool screen_rfq_batch → parse summary → Gmail HITL alert

---

Scoring Dimensions

Dimension	Max	Notes
Delivery window	30	≤1 day = 30pts, ≤2 day = 22pts
Total value	25	$50–$500 sweet spot
Set-aside match	20	WOSB = 20pts, SB = 14pts
Quantity	15	≤10 units = 15pts
Price clarity	10	Known price = 10pts

Thresholds: BID ≥ 65 | REVIEW 40–64 | SKIP < 40

---

Files

fast_award_screener_mcp/
├── server.py           ← FastMCP server + 3 tools
├── state.py            ← Single RFQState TypedDict (consolidated)
├── requirements.txt
├── nodes/
│   ├── __init__.py
│   ├── parse_rfq.py        ← Node 1: PDF parsing
│   ├── check_flags.py      ← Node 2: Disqualifying clauses
│   ├── score_opportunity.py ← Node 3: Viability scoring
│   └── lookup_grainger.py  ← Node 4: Grainger price lookup
└── README.md