entity-resolve
Fuzzy entity resolution and dedupe for names, addresses, and company records. $0.02/call via x402.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~187Token（工具定義）
~1.2 KB典型回應大小
極小的注意力影響（128k 上下文的 0.15%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"entity-resolve": {
"url": "https://entity-resolve.x402supply.com/mcp"
}
}
}遠端端點
https://entity-resolve.x402supply.com/mcpstreamable-http它能做什麼
工具清單
工具（1）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟡resolve(records, options)
Fuzzy-dedupe a list of records into clusters of likely-duplicate entities. Blocks by normalized token prefix, scores with Jaro-Winkler + token-set matching (exact on email/phone), unions matches above threshold, and returns a merged canonical record per cluster with a confidence score. Deterministic, no LLM calls.
輸入結構描述
{
"type": "object",
"properties": {
"records": {
"type": "array",
"items": {},
"minItems": 1,
"maxItems": 10000
},
"options": {
"type": "object",
"properties": {
"threshold": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.82
},
"keys": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1
}
},
"additionalProperties": false
}
},
"required": [
"records"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據
近期觀測
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具