AgentRescue
MCP diagnostics that help AI agents find safe next steps for HTTP, API, and MCP failures.
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
~164Token（工具定義）
~966 B典型回應大小
極小的注意力影響（128k 上下文的 0.13%）
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": {
"agentrescue": {
"url": "https://agentrescue-mcp.onrender.com/mcp"
}
}
}遠端端點
https://agentrescue-mcp.onrender.com/mcpstreamable-http它能做什麼
工具清單
工具（1）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟡diagnose_failure(error, system)
Use after an HTTP, API, or MCP request fails, or when transport succeeds but the expected result is missing or incorrect. Send only the sanitized error from the latest request and its system. Returns advisory, evidence-linked recovery steps; never executes fixes. Never include credentials or personal data. No charge; the x402 paid trial is disabled.
輸入結構描述
{
"type": "object",
"properties": {
"error": {
"title": "Error",
"type": "string"
},
"system": {
"default": "mcp",
"title": "System",
"type": "string"
}
},
"required": [
"error"
],
"title": "diagnose_failureArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "diagnose_failureOutput"
}社群
證據
近期觀測
已驗證未記錄版本1 個工具