Content Calendar Agent by Nova (CIVAI)

I create markdown content calendars and export them as PDFs via PDF Generator MCP

사용해야 할까요

품질 및 안전성

A
설명 품질
97%
스키마 완전성
96%
이름 품질
78%
오염 위험
100%
권한 일치
100%
프로토콜 준수
100%

발견 사항 (2)

  • LOWTool 'slide__converse' description lacks action verbslide__converse에서
  • LOWTool 'slide__generate_multiple_graphics' name length outside 3-30 rangeslide__generate_multiple_graphics에서

도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.

컨텍스트 비용

~1,042토큰 (도구 정의)
~939 B일반적인 응답 크기
중간 정도의 주의 영향 (128k 컨텍스트의 0.81%)

이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.

설치

원클릭 설치

`claude_desktop_config.json` 파일에 다음을 추가하세요:

{
  "mcpServers": {
    "content-calendar-agent": {
      "url": "https://nova.civai.co/mcp/agents/content-calendar-agent"
    }
  }
}

원격 엔드포인트

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

할 수 있는 일

도구 목록

도구 (9)

🟢 읽기 전용🟡 쓰기🔴 삭제⚪ 알 수 없음
🟢pdf__list_previews(notification_message)

List all stored PDF drafts in this session. Returns previews[{preview_id, title}], count, and most_recent_preview_id. Use when the user taps List PDFs or asks which drafts exist. Does not show document body — follow with get_preview after they pick.

입력 스키마

{
  "type": "object",
  "properties": {
    "notification_message": {
      "type": "string",
      "description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
    }
  },
  "required": [
    "notification_message"
  ]
}
🟢pdf__get_preview(preview_id, notification_message)

Preview PDF button. Call with no args first: if one draft exists, returns document_markdown; if multiple, returns needs_selection + previews — emit_display layout P (interaction_mode none) numbered picker only. NEVER collect_user_input or emit_display input for preview_id. After user replies with a number/title, call again with preview_id.

입력 스키마

{
  "type": "object",
  "properties": {
    "preview_id": {
      "type": "string",
      "description": "Optional. Omit on first Preview PDF tap so the tool can list drafts. Pass only after the user picks from the numbered list (or when chat already has a clear id)."
    },
    "notification_message": {
      "type": "string",
      "description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
    }
  },
  "required": [
    "notification_message"
  ]
}
🟡pdf__preview_document(title, content, update_preview_id, notification_message)

Write or revise draft markdown into session storage (creates preview_id). Agent-only — not a suggestion button. Use when the user asks to create/write/edit document content. For showing an existing draft use get_preview (Preview PDF). Never put emit_display chrome into content.

입력 스키마

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Document title (real topic title, not 'Preview')"
    },
    "content": {
      "type": "string",
      "description": "Full substantive markdown for the PDF pages (use --- between pages; each page needs a heading). Must be the document the user requested — never UI phrases like 'Here is a preview of your PDF document.'"
    },
    "update_preview_id": {
      "type": "string",
      "description": "When the user asks to adjust an existing preview, set this to that preview's preview_id. Omit to create a new preview."
    },
    "notification_message": {
      "type": "string",
      "description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
    }
  },
  "required": [
    "content",
    "notification_message"
  ]
}
⚪pdf__generate_pdf(preview_id, notification_message)

Generate a PDF from a preview. Call with no args first: if multiple previews exist, returns needs_selection + previews (title + preview_id) — ask the user which one, then call again with preview_id. If only one preview exists, generates it immediately. Returns pdf_url when generated.

입력 스키마

{
  "type": "object",
  "properties": {
    "preview_id": {
      "type": "string",
      "description": "Unique preview_id from a prior preview_document result. Omit to list choices (when multiple) or generate the only/last preview."
    },
    "notification_message": {
      "type": "string",
      "description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
    }
  },
  "required": [
    "notification_message"
  ]
}
🔴pdf__delete_preview(preview_id, notification_message)

Delete one stored PDF draft by preview_id from this chat session only. Hidden from suggestion buttons — agent-only. Returns deleted true/false. Does not remove already-generated public PDF files. Never accept path-like ids.

입력 스키마

{
  "type": "object",
  "properties": {
    "preview_id": {
      "type": "string",
      "description": "Hex preview_id from list_previews / get_preview in THIS session only"
    },
    "notification_message": {
      "type": "string",
      "description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
    }
  },
  "required": [
    "preview_id",
    "notification_message"
  ]
}
⚪slide__generate_single_graphic(detail)

🖼️ Slidegen: generate single graphic

입력 스키마

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Specific parameters for this action."
    }
  }
}
⚪slide__generate_image(detail)

🖼️ Slidegen: generate image

입력 스키마

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Specific parameters for this action."
    }
  }
}
⚪slide__generate_multiple_graphics(detail)

🖼️ Slidegen: generate multiple graphics

입력 스키마

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Specific parameters for this action."
    }
  }
}
⚪slide__converse(reply_hint)

Reply conversationally when the request is ambiguous or needs clarification.

입력 스키마

{
  "type": "object",
  "properties": {
    "reply_hint": {
      "type": "string",
      "description": "Optional hint for the conversational reply."
    }
  }
}

권장 프롬프트

retrieve_data
Get details about [item] from Content Calendar Agent by Nova (CIVAI)
예상 도구: bgpt_pdf_generator__get_preview
list_items
List all [items] available in Content Calendar Agent by Nova (CIVAI)
예상 도구: bgpt_pdf_generator__list_previews
explore_workflow
List available [items], then get details for each one using Content Calendar Agent by Nova (CIVAI)
예상 도구: bgpt_pdf_generator__list_previewsbgpt_pdf_generator__get_preview
fetch_info
Fetch [information type] using Content Calendar Agent by Nova (CIVAI)
예상 도구: bgpt_pdf_generator__get_preview
browse_collection
Show me the [collection] from Content Calendar Agent by Nova (CIVAI)
예상 도구: bgpt_pdf_generator__list_previews

커뮤니티

이 서버 평가하기

증거

최근 관측

검증됨버전이 기록되지 않음도구 9개
검증됨버전이 기록되지 않음도구 9개
검증됨버전이 기록되지 않음도구 9개