AgentRescue
MCP diagnostics that help AI agents find safe next steps for HTTP, API, and MCP failures.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~164token 数（工具定义）
~966 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.13%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"agentrescue": {
"url": "https://agentrescue-mcp.onrender.com/mcp"
}
}
}远程端点
https://agentrescue-mcp.onrender.com/mcpstreamable-http它能做什么
工具清单
工具（1）
🟢 只读🟡 写入🔴 删除⚪ 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.
输入模式
{
"type": "object",
"properties": {
"error": {
"title": "Error",
"type": "string"
},
"system": {
"default": "mcp",
"title": "System",
"type": "string"
}
},
"required": [
"error"
],
"title": "diagnose_failureArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "diagnose_failureOutput"
}社区
证据
最近观测
已验证未记录版本1 个工具