NumProof
Deterministic signed verification of numeric & financial claims for AI agents & spreadsheets.
我該用這個嗎
品質與安全性
B
發現項目(1)
- LOW在 diff_rows 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~251Token(工具定義)
~314 B典型回應大小
極小的注意力影響(128k 上下文的 0.20%)
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": {
"numproof": {
"command": "uvx",
"args": [
"numproof"
]
}
}
}可執行的套件
pypinumproof
0.1.1stdio遠端端點
https://numproof.com/mcpstreamable-http它能做什麼
工具清單
工具(4)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪verify_claim(claim)
Exactly verify a math/finance claim (VERIFY/REFUTE/ABSTAIN) with a counterexample when false. Use before trusting any AI-produced number, sum, percentage, or formula.
輸入結構描述
{
"type": "object",
"properties": {
"claim": {
"type": "string"
}
},
"required": [
"claim"
]
}⚪audit_rows(rows)
Audit spreadsheet-like rows for footing, balance-sheet ties, common margins, and cell provenance.
輸入結構描述
{
"type": "object",
"properties": {
"rows": {
"type": "array"
}
},
"required": [
"rows"
]
}⚪diff_rows(rows_before, rows_after)
Compare two report versions by numeric row labels with provenance.
輸入結構描述
{
"type": "object",
"properties": {
"rows_before": {
"type": "array"
},
"rows_after": {
"type": "array"
}
},
"required": [
"rows_before",
"rows_after"
]
}⚪covenant_rules(rows, rules, rule_pack)
Evaluate threshold/covenant rules over spreadsheet-like rows with provenance. Use either rules or rule_pack.
輸入結構描述
{
"type": "object",
"properties": {
"rows": {
"type": "array"
},
"rules": {
"type": "array"
},
"rule_pack": {
"type": "string"
}
},
"required": [
"rows"
]
}社群
證據
近期觀測
已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具