Google Docs Agent by Nova (CIVAI)
I do everything related to Google Docs
我该使用它吗
质量与安全性
B
发现（5）
- LOWTool 'google_docs__converse' description lacks action verb在 google_docs__converse 中
- LOWTool 'deep_research__conduct-deep-research' doesn't follow camelCase/snake_case在 deep_research__conduct-deep-research 中
- LOWTool 'deep_research__conduct-deep-research' name length outside 3-30 range在 deep_research__conduct-deep-research 中
- LOWTool 'deep_research__generate-research-report' doesn't follow camelCase/snake_case在 deep_research__generate-research-report 中
- LOWTool 'deep_research__generate-research-report' name length outside 3-30 range在 deep_research__generate-research-report 中
基于对工具定义和协议合规性的自动分析。
上下文开销
~634token 数（工具定义）
~701 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.50%）
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": {
"google-docs-agent": {
"url": "https://nova.civai.co/mcp/agents/google-docs-agent"
}
}
}远程端点
https://nova.civai.co/mcp/agents/google-docs-agentstreamable-http它能做什么
工具清单
工具（8）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟡google_docs__create_doc(detail)
Run Google docs action: create doc
输入模式
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}🟢google_docs__list_docs(detail)
Run Google docs action: list docs
输入模式
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}🟢google_docs__get_doc(detail)
Run Google docs action: get doc
输入模式
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}⚪google_docs__rewrite_doc(detail)
Run Google docs action: rewrite doc
输入模式
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}🔴google_docs__delete_doc(detail)
Run Google docs action: delete doc
输入模式
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}⚪google_docs__converse(reply_hint)
Reply conversationally when the request is ambiguous or needs clarification.
输入模式
{
"type": "object",
"properties": {
"reply_hint": {
"type": "string",
"description": "Optional hint for the conversational reply."
}
}
}🟢deep_research__conduct-deep-research(topic, objective, breadth, depth, max_total_queries, ...)
Conduct deep, iterative research on a topic by generating multiple search queries, processing the results, and recursively exploring new research directions.
输入模式
{
"type": "object",
"properties": {
"topic": {
"type": "string",
"description": "The main topic or question to research"
},
"objective": {
"type": "string",
"description": "The specific goal or objective of the research"
},
"breadth": {
"type": "integer",
"description": "Number of search queries per research direction (1-5)",
"default": 3,
"minimum": 1,
"maximum": 5
},
"depth": {
"type": "integer",
"description": "Depth of recursive exploration (0-2)",
"default": 1,
"minimum": 0,
"maximum": 2
},
"max_total_queries": {
"type": "integer",
"description": "Maximum number of search queries to process (2-5)",
"default": 2,
"minimum": 2,
"maximum": 5
},
"max_duration_seconds": {
"type": "integer",
"description": "Maximum duration for the research process in seconds (60-300)",
"default": 120,
"minimum": 60,
"maximum": 300
},
"connection_id": {
"type": "string",
"description": "Optional connection ID for the user",
"default": ""
}
},
"required": [
"topic",
"objective"
]
}⚪deep_research__generate-research-report(research_data, objective)
Generate a comprehensive research report from existing research data.
输入模式
{
"type": "object",
"properties": {
"research_data": {
"type": "string",
"description": "The research data and findings to include in the report"
},
"objective": {
"type": "string",
"description": "The specific goal or objective of the report"
}
},
"required": [
"research_data",
"objective"
]
}推荐提示词
retrieve_data
Get details about [item] from Google Docs Agent by Nova (CIVAI)
预期工具：
google_docs__get_docfind_specific
Find [specific item] using Google Docs Agent by Nova (CIVAI)
预期工具：
deep_research__conduct-deep-researchfetch_info
Fetch [information type] using Google Docs Agent by Nova (CIVAI)
预期工具：
google_docs__get_docsearch_research
Search for information about [topic] using Google Docs Agent by Nova (CIVAI)
预期工具：
deep_research__conduct-deep-researchlist_items
List all [items] available in Google Docs Agent by Nova (CIVAI)
预期工具：
google_docs__list_docs社区
证据
最近观测
已验证未记录版本8 个工具
已验证未记录版本8 个工具