graphrag-ts citation provenance
Source-tiered retraction and citation judgments for DOIs; abstains when evidence is thin.
我該用這個嗎
品質與安全性
B
根據工具定義與協定合規性的自動化分析。
上下文成本
~178Token(工具定義)
~99 B典型回應大小
極小的注意力影響(128k 上下文的 0.14%)
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": {
"graphrag-ts": {
"url": "https://mcp.ashesborn.cloud/mcp"
}
}
}遠端端點
https://mcp.ashesborn.cloud/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢integrity_paper_status
Get retraction status and identity for a paper.
輸入結構描述
{
"type": "object",
"properties": {}
}🟡retraction_propagation
Judge whether retraction evidence propagates to a paper. Paid: $0.02 per call (x402 on Base, POST /api/v1/judge); a keyed MCP session also unlocks it.
輸入結構描述
{
"type": "object",
"properties": {}
}🟡integrity_evidence_audit
Audit the evidence path, source tiers, and conflicts for a paper. Paid: $0.10 per call (x402 on Base, POST /api/v1/judge); a keyed MCP session also unlocks it.
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據
近期觀測
已驗證未記錄版本3 個工具