AILANG Parse

Deterministic DOCX/PPTX/XLSX/PDF parser: track changes, comments, headers, footers, merged cells.

使うべきか

品質と安全性

A
説明の品質
97%
スキーマの完全性
82%
命名の品質
84%
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%

検出事項(1)

  • LOWTool 'mcpEstimate' description lacks action verbmcpEstimate 内

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

~1,612トークン数(ツール定義)
~675 B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 1.26%)

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": {
    "parse": {
      "command": "npx",
      "args": [
        "@ailang/parse"
      ]
    }
  }
}

実行可能なパッケージ

npm@ailang/parse0.13.1stdio
pypiailang-parse0.13.1stdio

リモートエンドポイント

https://docparse.ailang.sunholo.com/mcp/streamable-http

できること

ツール一覧

ツール(10)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟡editDocument(apiKey, deltas, filepath)

Parse a document, apply JSON edit deltas, and return the modified blocks as JSON (same format as POST /api/v1/parse with outputFormat=blocks). filepath: uploaded file path (multipart upload). deltas: JSON array of edit operations — see edit_apply.ail for format. Empty array or "" → round-trip (parse + return unchanged blocks). apiKey: dp_ API key. Response: modified blocks JSON. Use the AILANG SDK or CLI to generate a file from the returned blocks (e.g. ailang run ... --convert output.docx). Only deterministic office formats are supported (docx, pptx, xlsx, odt, odp, ods). AI-required formats (pdf, image, audio, video) are rejected.

入力スキーマ

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string"
    },
    "deltas": {
      "type": "string"
    },
    "filepath": {
      "type": "string"
    }
  },
  "required": [
    "filepath",
    "deltas",
    "apiKey"
  ]
}
🟡getUploadUrl(apiKey, filename, mimeType)

Request a pre-authenticated GCS upload URL for direct file upload. Business tier only. The returned URL allows the client to PUT file content directly to GCS, bypassing the 32MB Cloud Run request limit. After upload, pass the gcs_ref to POST /api/v1/parse.

入力スキーマ

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string"
    },
    "filename": {
      "type": "string"
    },
    "mimeType": {
      "type": "string"
    }
  },
  "required": [
    "filename",
    "mimeType",
    "apiKey"
  ]
}
🟡mcpAccount(action, apiKey)

View account info, pricing, entitlements, or list keys. Actions: "status" (default) → tier, quota, usage from /me/entitlements "pricing" → public pricing tiers (no auth required) "keys" → list user's API keys with per-key usage "usage" → alias for "keys" (per-key usage is shown there) "history" → whether request history (parsed output kept for replay) is on for this account "history_on" / "history_off" → change it for the account and all its keys Deleting history is deliberately not an MCP action: it stays on POST /api/v1/requests/delete and the dashboard.

入力スキーマ

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string"
    },
    "apiKey": {
      "type": "string"
    }
  },
  "required": [
    "apiKey",
    "action"
  ]
}
🟢mcpAuth(label)

Start device authorization to get an API key. Returns device_code, user_code, and verification URL. The agent should display the verification URL to the user, who signs in and approves the code. Then call mcpAuthPoll with the device_code. MCP wrappers don't have HTTP request headers, so provenance is empty here.

入力スキーマ

{
  "type": "object",
  "properties": {
    "label": {
      "type": "string"
    }
  },
  "required": [
    "label"
  ]
}
⚪mcpAuthPoll(deviceCode)

Poll for device authorization completion. Returns "pending" (keep polling every 5s), "approved" (with api_key and tier), or "expired" (start over with mcpAuth).

入力スキーマ

{
  "type": "object",
  "properties": {
    "deviceCode": {
      "type": "string"
    }
  },
  "required": [
    "deviceCode"
  ]
}
🟡mcpConvert(apiKey, input, outputFormat, outputPath)

Convert a document to another format. Targets: html, md, qmd, docx, pptx, xlsx, odt, odp, ods. `input` is a file path, a sample_id, an https:// URL, or a gs:// ref (Business tier). The converted file comes back as base64 in the JSON response rather than written to disk, so decode `content` to get the bytes. `outputPath` is accepted but ignored; it stays in the signature because removing it would change the auto-generated MCP tool schema for existing clients.

入力スキーマ

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string"
    },
    "input": {
      "type": "string"
    },
    "outputFormat": {
      "type": "string"
    },
    "outputPath": {
      "type": "string"
    }
  },
  "required": [
    "input",
    "outputFormat",
    "outputPath",
    "apiKey"
  ]
}
⚪mcpEstimate(filepath, outputFormat)

Estimate cost and latency for parsing a document. Accepts a file path or sample_id. No auth required.

入力スキーマ

{
  "type": "object",
  "properties": {
    "filepath": {
      "type": "string"
    },
    "outputFormat": {
      "type": "string"
    }
  },
  "required": [
    "filepath",
    "outputFormat"
  ]
}
🟢mcpFormats(_)

Supported formats, samples, and service capabilities. No auth required. Delegates to package implementation. Single source of truth lives in pkg/sunholo/ailang_parse/services/mcp/tools — since ailang_parse 0.39.x the response carries a runtime capability block (state, not intent), which is why this is no longer pure: it reads env and probes the runtime (Process).

入力スキーマ

{
  "type": "object",
  "properties": {
    "_": {
      "type": "string"
    }
  },
  "required": [
    "_"
  ]
}
🟢mcpParse(apiKey, filepath, outputFormat, requestId)

Parse a document. Accepts a file path or sample_id (e.g. "sample_docx_formatting"). The hosted server requires a valid dp_ API key — get one via mcpAuth. Output formats: blocks (default), markdown, html, a2ui. requestId is reserved for future replay support.

入力スキーマ

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string"
    },
    "filepath": {
      "type": "string"
    },
    "outputFormat": {
      "type": "string"
    },
    "requestId": {
      "type": "string"
    }
  },
  "required": [
    "filepath",
    "outputFormat",
    "apiKey",
    "requestId"
  ]
}
🟡submit_feedback(ailang_version, auto_dispatch, body, category, contact, ...)

Anonymous bug report / feature request / docs gap, queued for human review. Default routing: `public-feedback` inbox (general AILANG). Pass `package="vendor/name"` (e.g. "sunholo/auth") to route to that package's `pkg:vendor/name` inbox where its autonomous agent watches. Categories: bug, feature, docs, limitation. Body limit 10KB, snippet limit 4KB. Optional contact field for follow-up; opaque to the server. Set `auto_dispatch=true` to authorize the package agent to act on your submission immediately (default false — files for human triage; pkg-feedback agent template lands in a separate sprint).

入力スキーマ

{
  "type": "object",
  "properties": {
    "ailang_version": {
      "type": "string",
      "description": "The reporter's CLI version (free-form, used for triage)"
    },
    "auto_dispatch": {
      "type": "boolean",
      "description": "Authorize the receiving package's autonomous agent to act on this submission. Default false (files for human triage). Tagged on the Pub/Sub notification as category=auto:<original> for coordinator filtering."
    },
    "body": {
      "type": "string",
      "description": "Full description (≤10 KB)"
    },
    "category": {
      "type": "string",
      "description": "bug | feature | docs | limitation"
    },
    "contact": {
      "type": "string",
      "description": "Optional follow-up address (free-form, opaque to the server)"
    },
    "package": {
      "type": "string",
      "description": "Optional vendor/name (e.g. \"sunholo/auth\") to route to that package's pkg:vendor/name inbox. Empty = general AILANG feedback."
    },
    "snippet": {
      "type": "string",
      "description": "Optional code/error snippet (≤4 KB)"
    },
    "title": {
      "type": "string",
      "description": "Short title for the report"
    }
  },
  "required": [
    "title",
    "body",
    "category",
    "ailang_version"
  ]
}

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 10 件
検証済みバージョンは記録されていませんツール 10 件