RunBoth
Ask runboth.dev in plain language: what RunBoth does, how to install it, and its limits.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"agent": {
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}远程端点
https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcpstreamable-http它能做什么
工具清单
工具（3）
🟡ask(query, site, generate_mode)
Ask runboth.dev a question in plain language and get the answer from its own pages, with sources. RunBoth is a zero-dependency Python tool that finds out what a refactor actually changed by running the old and the new code on generated inputs and comparing seven behaviour channels, rather than reading the diff. Covers: detecting behavioural change from a Python refactor; differential execution and the seven channels it compares; installing RunBoth and running it as a commit hook or GitHub Action; what a CHANGED, NO CHANGE or ABSTAINED verdict means; how RunBoth was red-teamed and where its limits are. For example: How do I find out what my Python refactor actually changed in behaviour? Answers come back as ranked pages from runboth.dev with a URL, a score and a one-line reason each.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The question, in plain language. For example: How do I find out what my Python refactor actually changed in behaviour?"
},
"site": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional list of sites to search. If not provided, searches all configured sites"
},
"generate_mode": {
"type": "string",
"enum": [
"list",
"generate",
"summarize"
],
"description": "The type of response to generate",
"default": "list"
}
},
"required": [
"query"
]
}🟢list_sites
List the sites this endpoint answers for (runboth.dev).
输入模式
{
"type": "object",
"properties": {}
}🟢trust_lookup(target, top_k)
Look up what AI agents recorded after calling a website or an MCP endpoint: which capability they used, whether it worked, how long it took, and what they learned. Read-only, no key. Use it before you trust an endpoint you have never called, including this one.
输入模式
{
"type": "object",
"properties": {
"target": {
"type": "string",
"description": "A domain or endpoint URL, for example runboth.dev or https://host/mcp"
},
"top_k": {
"type": "integer",
"description": "How many records to return, 1 to 25",
"default": 8
}
},
"required": [
"target"
]
}社区
证据