flatmark

Document to Markdown MCP server: PDF, Word, PowerPoint, Excel and HTML, with OCR for large files.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
94%
命名の品質
100%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~1,182トークン数(ツール定義)
~2.4 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.92%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "flatmark": {
      "url": "https://api.flatmark.dev/mcp/"
    }
  }
}

リモートエンドポイント

https://api.flatmark.dev/mcp/streamable-http

できること

ツール一覧

ツール(3)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢convert_document(filename, content_base64, file)

Convert a document up to 8 MB to Markdown and return it directly. Pass the file as base64 in `content_base64`, or as a download link in `file`, and its name in `filename`. The extension decides the type: .pdf, .docx, .pptx, .xlsx, .html, .htm or .txt. Returns `markdown` and `meta` (`filename`, `length` in characters). PDFs come back as plain text without headings and without OCR. For scans, tables and page numbers, use `submit_conversion_job`. Works without an API key at the anonymous rate limit. Credits: 1 per call.

入力スキーマ

{
  "type": "object",
  "properties": {
    "filename": {
      "description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read.",
      "type": "string"
    },
    "content_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The file content, base64-encoded. Up to 8 MB before encoding."
    },
    "file": {
      "properties": {
        "download_url": {
          "description": "A public https URL of the file.",
          "type": "string"
        },
        "file_id": {
          "description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name.",
          "type": "string"
        },
        "mime_type": {
          "type": "string"
        },
        "file_name": {
          "type": "string"
        }
      },
      "required": [
        "download_url",
        "file_id"
      ],
      "type": "object",
      "default": null,
      "description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL."
    }
  },
  "required": [
    "filename"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟡submit_conversion_job(filename, content_base64, file, webhook_url)

Queue a document up to 25 MB and 200 pages for conversion with OCR and tables. Pass the file as base64 in `content_base64`, or as a download link in `file`, and its name in `filename` (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). Returns `job_id`, `status` and `result_url`. Call `get_conversion_job` with the `job_id` until `status` is `succeeded` or `failed`. A conversion may take up to about 2 minutes. Optional `webhook_url`: a public http or https URL that receives a POST with the job's final state. The request carries `X-Appkit-Signature: sha256=<hex>`, an HMAC-SHA256 of the raw body keyed with the returned `webhook_secret` (shown only once). 3 delivery attempts. Requires an API key. The credits are refunded if the job fails. The uploaded file is deleted when the job finishes. Results are kept for 7 days after submission. Credits: 10 per call.

入力スキーマ

{
  "type": "object",
  "properties": {
    "filename": {
      "description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read.",
      "type": "string"
    },
    "content_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The file content, base64-encoded. Up to 25 MB before encoding."
    },
    "file": {
      "properties": {
        "download_url": {
          "description": "A public https URL of the file.",
          "type": "string"
        },
        "file_id": {
          "description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name.",
          "type": "string"
        },
        "mime_type": {
          "type": "string"
        },
        "file_name": {
          "type": "string"
        }
      },
      "required": [
        "download_url",
        "file_id"
      ],
      "type": "object",
      "default": null,
      "description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL."
    },
    "webhook_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional. A public http or https URL that receives the job's final state."
    }
  },
  "required": [
    "filename"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢get_conversion_job(job_id)

Check a queued conversion job you submitted. Returns `job_id` and `status` (`queued`, `running`, `succeeded` or `failed`). A succeeded job includes the `markdown` when it is under 100 KB, otherwise a `result_url` to download it (also free). A failed job includes `error`, one sentence with the reason. Results are deleted 7 days after submission. An expired result is reported in `error`. Requires an API key. Credits: free. This tool is not metered.

入力スキーマ

{
  "type": "object",
  "properties": {
    "job_id": {
      "description": "The `job_id` returned by `submit_conversion_job`.",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 3 件