MCP MeasureMCP Measure

索引已觀測

Research Agent by Nova (CIVAI)

I do everything related to research and reports

我該用這個嗎

品質與安全性

B
說明品質
93%
結構描述完整度
93%
命名品質
55%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目（5）

  • LOWTool 'google_search__converse' description lacks action verb在 google_search__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

根據工具定義與協定合規性的自動化分析。

上下文成本

~432Token（工具定義）
~1022 B典型回應大小
極小的注意力影響（128k 上下文的 0.34%）

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": {
    "research-agent": {
      "url": "https://nova.civai.co/mcp/agents/research-agent"
    }
  }
}

遠端端點

https://nova.civai.co/mcp/agents/research-agentstreamable-http

它能做什麼

工具清單

工具（4）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢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.

輸入結構描述

{
  "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.

輸入結構描述

{
  "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"
  ]
}
🟢google_search__search(query)

Run live Google search and summarize results.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    }
  },
  "required": [
    "query"
  ]
}
🟢google_search__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

search_research
Search for information about [topic] using Research Agent by Nova (CIVAI)
預期的工具： deep_research__conduct-deep-research
find_specific
Find [specific item] using Research Agent by Nova (CIVAI)
預期的工具： deep_research__conduct-deep-research

社群

為此伺服器評分

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