justin
1409c2617d
Sitemap-driven scraper for goldenharvestseeds.com. Walks sitemap-ghs-hybrids.xml to discover product URLs under /products/corn/ and /products/soybean/ (~89 + 86 = 175 candidates). Per-variety detail parsed from server-rendered HTML: - product code (from <h1> / <title>) - positioning (from <meta name="Description">) - maturity (from <div class="product-label"><div class="right">): integer days for corn, decimal MG for soybeans - traits derived from product-code suffix (XF, E3, VIP3, GT, Z, etc.) - 9-row disease tolerance bar chart (#dvDiseaseTolerance) where data-percentage / 10 = rating on 1-9 (9 = best) scale - 9-row agronomic characteristics bar chart (#dvAgronomicChar) - recommended environment list (.AgronomicMange — upstream typo) - all 2-column tables (plant description, seed quality, herbicide responses, Phytophthora gene, SCN race coverage) - tech-sheet PDF URL from live HTML (not sitemap — that's stale) 302 redirects to /product-finder treated as "discontinued" and skipped (Golden Harvest still sitemap-lists some retired SKUs). Rating scale: 1-9 (9 = best) — same as Bayer despite recon's "9-to-1" descriptor (that referred to chart-axis direction, not numeric meaning). _scale_direction is set explicitly so the chunker stays forward-compatible. PDFs are NOT downloaded (recon flagged ~14MB each); tech-sheet URLs are captured in the sidecar for future enrichment. Smoke-tested all branches: 4 corn varieties (E085Z5, E092W5, E094Z4, E095D3, E097K6, E100A3) with full 6 characteristics groups + tech-sheet URL; 3 soy varieties (GH00864XF MG 0.08, GH00973E3 MG 0.09, GH0225XF MG 0.2) with disease + agronomic bars; 302 redirects skipped cleanly. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
seed-mcp
MCP server over the public catalogs of major US row-crop seed
vendors — corn, soybeans, wheat. Sibling project to
crop-chem-docs
(pesticide labels), feeding the same Drawbar farm-advisor AI.
The server exposes per-variety records with agronomic ratings, disease tolerance, trait stack, maturity, and regional notes — so the advisor can answer questions like "which corn hybrid for sandy soil, drought-prone, RM ≤105 in northeast Iowa?" without rummaging through individual brand sites.
Vendor coverage
| Vendor | Verdict | Varieties | Notes |
|---|---|---|---|
| Bayer seeds (DEKALB + Asgrow + WestBred) | 🟢 | ~475 | Same cropscience.bayer.us Next.js infra as crop-chem-docs |
| Golden Harvest (Syngenta) | 🟢 | ~175 | Sitemap + server-rendered HTML + Syngenta CDN PDFs |
| NK (Syngenta) | 🟢 | 29 | Shares PDF fetcher with Golden Harvest |
| AgriPro (Syngenta wheat) | 🟢 | 24 | Drupal Views, server-rendered |
| Beck's PFR | 🟡 | 2,089 | Public Sanity GROQ API (no auth) |
| Beck's products | 🟡 | 860 | Identity-only until SeedIQ XHR sniffed |
| Pioneer (Corteva) | 🔴 | — | ToS bans automation — curated fallback lesson instead |
Quick start
git clone https://git.jpaul.io/justin/seed-mcp.git
cd seed-mcp
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt
# Run one scraper
python -m scrape.runner --source bayer_seeds --force
# Rebuild indexes
python -m rag.index --rebuild
# Local MCP server (stdio for Claude Desktop dev)
python -m docs_mcp.server --transport stdio
Tools exposed
| Tool | Purpose |
|---|---|
search_docs |
Hybrid + rerank variety search with crop / RM / trait / region filters |
get_page |
Full variety record by (source, source_key) |
list_versions |
Discover crops, brands, traits, RM/MG ranges, wheat classes |
corpus_status |
Counts + freshness; useful for health probes |
crop_seed_api_lessons |
Curated agronomy lessons — Pioneer fallback, disease-scale normalization, regional placement heuristics |
Build phases
This is a clone of docs-mcp-template.
The 13 phases in PLAN.md apply:
| Phase | Status |
|---|---|
| 0 — scaffold | done |
| 1 — first scraper (bayer_seeds) | next |
| 2 — chunk + index | pending |
| 3 — baseline MCP tools | template defaults |
| 4-5 — Dockerfile + CI | done (placeholders filled) |
| 6 — reranker | shares llama-rerank sidecar with crop-chem-docs |
| 7 — eval harness | pending (curate ~25 queries) |
| 8 — hybrid search | done (template) |
| 9 — diff_versions, list_cluster | optional |
11 — crop_seed_api_lessons curated layer |
pending |
See CLAUDE.md for the canonical sidecar schema and the
disease-scale-normalization gotcha (Golden Harvest is reversed).
Infrastructure
- Registry:
git.jpaul.io/justin/seed-mcp:latest(Watchtower) /:corpus-YYYY.MM.DD(production pin) - Embedder: shared Ollama pool with crop-chem-docs (Gitea-host GPUs + Windows Ollama; CI never hits trashpanda's production Ollama)
- Reranker: shared
llama-reranksidecar on trashpanda's Tesla P4 (one container, both MCPs use it) - PRODUCT_NAME:
crop_seed(notseed_mcp— used in Chroma collection, BM25 db filename, andcrop_seed_api_lessonstool)