@nikeandocean/carbon-factor-matcher 2.1.0 → 2.2.0

package/README.md

@@ -9,18 +9,18 @@ An MCP (Model Context Protocol) server that connects AI agents with carbon emiss
 Carbon Factor Matcher helps AI agents find the most appropriate emission factors from standardized environmental databases. It uses a hybrid search algorithm:
 
 1. **Keyword + Embedding retrieval** — Field-weighted keyword scoring and semantic similarity to find candidate factors
-2. **Quality-based ranking** — 5-dimension data quality assessment to rank candidates
 
 The calling AI agent selects the best match from the ranked candidates. No external LLM API needed.
 
 ### Supported Databases
 
-- **ELCD** — European Reference Life Cycle Database (~600 factors, included in Free tier)
-- **ecoinvent 3.10** — Swiss Centre for Life Cycle Inventories (~21,000 factors, Pro license required)
+- **ELCD** — European Reference Life Cycle Database (500+ factors, included in Free tier)
+- **ecoinvent 3.10** — Swiss Centre for Life Cycle Inventories (6,000+ factors, Pro license required)
+- **MEE** — China Ministry of Ecology and Environment (48 provincial/grid factors, Pro license required)
 
 ### Key Features
 
-- 5-dimension data quality rating (technology, geography, source, time, factor type)
+- Hybrid keyword + embedding matching (DashScope text-embedding-v4)
 - Multi-language support (Chinese/English activity descriptions)
 - Zero configuration — works out of the box after installation
 - MCP-compatible — works with Claude, Cursor, Windsurf, Cline, Continue, and any MCP client
@@ -128,8 +128,8 @@ The Free tier works immediately after installation (300 queries/day, ELCD databa
 
 | Plan | Price | Features |
 |------|-------|----------|
-| **Free** | $0 | ELCD database (~600 factors), keyword search, 300 queries/day |
-| **Pro** | $5 (one-time) | ELCD + ecoinvent (~21,000 factors), hybrid matching with quality rating, unlimited queries |
+| **Free** | $0 | ELCD database (500+ factors), keyword search, 300 queries/day |
+| **Pro** | $5 (one-time) | ELCD + ecoinvent + MEE (6,370+ factors), hybrid keyword + embedding matching, unlimited queries |
 
 ### Purchase License Key
 
@@ -164,13 +164,13 @@ Note: No external LLM API configuration needed. The calling AI agent handles fin
 
 ### `factor_match`
 
-Match activity data to emission factors. Free tier uses keyword search; Pro tier uses hybrid embedding + quality ranking. Returns ranked candidates for the calling agent to select from.
+Match activity data to emission factors. Free tier uses keyword search; Pro tier uses hybrid keyword + embedding matching. Returns ranked candidates for the calling agent to select from.
 
 **Input:**
 ```json
 {
-  "activity_data": "Factory in Shenzhen, 10kV industrial electricity, 2024, semiconductor fab",
-  "top_k": 10
+  "activity_data": "electricity, medium voltage, industrial grid, China, Guangdong",
+  "top_k": 5
 }
 ```
 
@@ -179,14 +179,17 @@ Match activity data to emission factors. Free tier uses keyword search; Pro tier
 {
   "candidates": [
     {
-      "id": "elec-cn-south-10kv-2024",
-      "name": "Electricity, 10kV, South China Grid",
-      "value": 0.6101,
-      "unit": "kgCO2e/kWh",
-      "hybrid_score": 0.85,
-      "quality_ratings": {"tech_representativeness": 1, "source_reliability": 1, "...": "..."},
-      "quality_score": 0.9,
-      "final_score": 0.875
+      "name": "electricity, provincial grid, Guangdong (广东)",
+      "value": 0.4419,
+      "unit": "kgCO2/kWh",
+      "geography": {"location": "China, Guangdong (广东)"},
+      "source": "MEE (Ministry of Ecology and Environment), China",
+      "source_year": 2023,
+      "db_source": "mee",
+      "keyword_score": 0.8293,
+      "embedding_score": 0.6779,
+      "hybrid_score": 0.7233,
+      "final_score": 0.7233
     }
   ],
   "selection_guidance": "从候选列表中选择最匹配的排放因子..."

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nikeandocean/carbon-factor-matcher",
-  "version": "2.1.0",
+  "version": "2.2.0",
   "description": "MCP server for intelligent emission factor matching — connects AI agents with carbon emission factor databases (ELCD, ecoinvent)",
   "main": "index.js",
   "bin": {