docs
Search and fetch AgendaForge public documentation and marketing content. No authentication needed.
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
~225token 数(工具定义)
~792 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.18%)
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://mcp.agendaforge.app/mcp/docs"
}
}
}远程端点
https://mcp.agendaforge.app/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 AgendaForge public marketing and documentation content. Returns no account or private event data.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"description": "Words or a natural language phrase to search for."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 5,
"description": "Maximum number of ranked results to return."
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢fetch_doc(route)
Fetch one public AgendaForge markdown document by an exact route or URL from the public docs index.
输入模式
{
"type": "object",
"properties": {
"route": {
"type": "string",
"minLength": 1,
"description": "Exact route, canonical URL, or markdown URL present in the public docs index."
}
},
"required": [
"route"
],
"additionalProperties": false
}推荐提示词
search_research
Search for information about [topic] using docs
预期工具:
search_docsfind_specific
Find [specific item] using docs
预期工具:
search_docsretrieve_data
Get details about [item] from docs
预期工具:
fetch_docfetch_info
Fetch [information type] using docs
预期工具:
fetch_docresearch_workflow
Search for [topic], then get detailed information about the top results using docs
预期工具:
search_docsfetch_doc社区
证据
最近观测
已验证未记录版本2 个工具
已验证未记录版本2 个工具