Gmail Agent by Nova (CIVAI)
I do everything related to Gmail and productivity
我該用這個嗎
品質與安全性
B
發現項目(1)
- LOW在 gmail__converse 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~204Token(工具定義)
~356 B典型回應大小
極小的注意力影響(128k 上下文的 0.16%)
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"gmail-agent": {
"url": "https://nova.civai.co/mcp/agents/gmail-agent"
}
}
}遠端端點
https://nova.civai.co/mcp/agents/gmail-agentstreamable-http它能做什麼
工具清單
工具(4)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪gmail__compose_email(detail)
Run Google mail action: compose email
輸入結構描述
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}🟢gmail__read_single_email(detail)
Run Google mail action: read single email
輸入結構描述
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}⚪gmail__latest_emails(detail)
Run Google mail action: latest emails
輸入結構描述
{
"type": "object",
"properties": {
"detail": {
"type": "string",
"description": "Task-specific details from the objective."
}
}
}⚪gmail__converse(reply_hint)
Reply conversationally when the request is ambiguous or needs clarification.
輸入結構描述
{
"type": "object",
"properties": {
"reply_hint": {
"type": "string",
"description": "Optional hint for the conversational reply."
}
}
}建議的提示詞
retrieve_data
Get details about [item] from Gmail Agent by Nova (CIVAI)
預期的工具:
gmail__read_single_emailfetch_info
Fetch [information type] using Gmail Agent by Nova (CIVAI)
預期的工具:
gmail__read_single_email社群
證據
近期觀測
已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具