AILANG Parse

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

我该使用它吗

质量与安全性

A
描述质量
97%
模式完整度
82%
命名质量
84%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(1)

  • LOWTool 'mcpEstimate' description lacks action verb在 mcpEstimate 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,612token 数(工具定义)
~675 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.26%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

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

可运行的软件包

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

远程端点

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

它能做什么

工具清单

工具(10)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟡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.

输入模式

{
  "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.

输入模式

{
  "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.

输入模式

{
  "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.

输入模式

{
  "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).

输入模式

{
  "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.

输入模式

{
  "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.

输入模式

{
  "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).

输入模式

{
  "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.

输入模式

{
  "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).

输入模式

{
  "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"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本10 个工具
已验证未记录版本10 个工具