Open Creator Graph docs
How the Open Creator Graph works: records, confidence labels, AI consent, removals, reuse.
我该使用它吗
质量与安全性
A
发现(1)
- LOW在 fetch_doc 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~310token 数(工具定义)
~507 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.24%)
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": {
"docs": {
"url": "https://creatorgraph.sparkonomy.com/mcp/docs"
}
}
}远程端点
https://creatorgraph.sparkonomy.com/mcp/docsstreamable-http它能做什么
工具清单
工具(2)
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_docs(query, limit)
Search the Open Creator Graph's FAQ and machine documentation (llms.txt, llms-full.txt, reuse terms) for questions about how records, confidence labels, AI consent, removals and reuse work.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 5
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢fetch_doc(path)
Read one documentation page in full, as Markdown. `path` is a path search_docs returned, or one of /llms.txt, /llms-full.txt, /license.txt, /faqs/, /for-ai-and-search/, /how-we-source/, /editorial-policy/, /about-this-record/, /why-the-graph-exists/, /for-creators/, /for-agencies/, /changelog/.
输入模式
{
"type": "object",
"properties": {
"path": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"required": [
"path"
],
"additionalProperties": false
}社区
证据
最近观测
已验证未记录版本2 个工具