Tuatara Summarize
Extractive document summarizer: returns the text's own sentences, so it cannot add facts.
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
~336token 数（工具定义）
~2.4 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.26%）
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": {
"tuatara-summarize": {
"url": "https://cymetica.com/mcp/v1/summarize"
}
}
}远程端点
https://cymetica.com/mcp/v1/summarizestreamable-http它能做什么
工具清单
工具（1）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢summarize_document(text, sentence_count, ratio, max_tokens, context_control, ...)
Tuatara Summarize: extractive summary of a document. Returns the document's own sentences, chosen by a vector-association model, cut to sentence_count, a ratio of the sentences or a token budget; nothing is generated, so the summary cannot add facts. Use it to shrink long text before passing it to a chat model. Up to 200,000 characters per call; no account needed.
输入模式
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "the document (plain text or HTML)"
},
"sentence_count": {
"type": "integer",
"description": "number of sentences to keep (1-500)"
},
"ratio": {
"type": "number",
"description": "share of the sentences to keep, 0.05-0.9 (e.g. 0.2)"
},
"max_tokens": {
"type": "integer",
"description": "token budget for the summary (cl100k tokens)"
},
"context_control": {
"type": "string",
"description": "one word to steer the summary toward a subject"
},
"context_control_sensitivity_level": {
"type": "number",
"description": "0-10, how strongly the word steers (default 2)"
},
"mode": {
"type": "string",
"description": "auto (default), faithful, gs1, gs2, best, tuned or tuned-best"
},
"order": {
"type": "string",
"description": "document (default: original order) or rank (best first)"
}
},
"required": [
"text"
]
}社区
证据
最近观测
已验证未记录版本1 个工具