Skip to main content
Glama
doc-redactor

doc-redactor

by agxhub

doc-redactor

本地优先的多格式文档脱敏工具:检测 → 真删除 → 取证审计,全程零网络调用。 支持 PDF(文字型 + 扫描件)、DOCX、XLSX、PPTX、TXT/MD/CSV/JSON 等。 可作为 MCP server 接入 AgenticX 等任意支持 MCP 的 Agent 框架,或作为 Python 库直接使用。

格式路由采纳 AgenticX KB 的扩展名分类; 检测层格式无关(一份检测代码服务全部格式),执行层逐格式真删除。

能力矩阵

泄露面

PDF 文字型

PDF 扫描件

DOCX

XLSX

PPTX

TXT/MD

正文本体

内容流物理移除

OCR 定位 + 图像像素真删除

段落/表格 run 级替换(跨 run 重建)

全 sheet 单元格(含隐藏 sheet)

shape/表格/组合形状递归

直接替换

Logo / 嵌入图

SIFT 模板匹配(宽高比 + NCC 双校验)

同左

—

—

—

—

扫描页

自动识别(文本量阈值)→ RapidOCR

✓

—

—

—

—

元数据

docinfo + XMP 全清

同左

core.xml 属性

属性 + 透视缓存天然清除

core.xml 属性

无

修订记录

—

—

w:del/w:ins 全接受

—

—

—

批注

注释/表单

—

comments.xml 替换

单元格批注

—

—

页眉页脚/备注

—

—

页眉页脚(含首页/偶数页)

—

备注页

—

取证审计

对象流/隐藏文本/增量保存/logo 回扫

OCR 回扫

解压逐部件搜词 + 修订残留检查

同左 + 隐藏 sheet

同左

重读全文

检测层(全格式共享):关键词词典 + 正则(手机/身份证/邮箱/银行卡)+ spaCy 中文 NER(可选)。 OCR 文本经 NFKC 归一化后再检测(OCR 常把数字识别成全角),命中区域按字符占比切分,宁大勿漏。

Related MCP server: phi-redact-mcp

MCP 工具(两阶段安全设计)

  • redact_scan — 非破坏性扫描(自动识别格式),返回候选清单 + 元数据泄露 + 格式相关清单

  • redact_apply — 只执行确认过的词条清单(不吃自动判断)

  • redact_audit — 取证审计,交付前必须 PASS

  • extract_image — 提取 PDF 嵌入图像作为 logo 脱敏模板

  • glossary_list / add / remove — 敏感词词典闭环(~/.doc-redactor/glossary.json)

安全原则:Agent 永远不能静默决定"什么算敏感"——scan 出候选、用户确认、apply 只吃确认清单、audit 兜底。

安装

git clone https://github.com/agxhub/doc-redactor && cd doc-redactor
uv venv .venv --python 3.11
uv pip install --python .venv/bin/python -e ".[ner]"
.venv/bin/python -m spacy download zh_core_web_trf   # 可选:NER 检测

注册到 AgenticX

在 ~/.agenticx/mcp.json 添加:

{
  "mcpServers": {
    "doc-redactor": {
      "command": "/path/to/doc-redactor/.venv/bin/python",
      "args": ["mcp_server.py"],
      "cwd": "/path/to/doc-redactor",
      "timeout": 300.0
    }
  }
}

Python 库直接使用

from docredactor import scan_document, apply_redaction, audit_document

scan = scan_document("合同.docx", keywords=["张伟"], enable_ner=True)
# 用户确认候选后
apply_redaction("合同.docx", "合同_脱敏.docx", terms=["张伟", "13800138000"])
report = audit_document("合同_脱敏.docx", terms=["张伟", "13800138000"])
assert report["verdict"] == "PASS"

Roadmap

  • 旧版二进制 Office(.doc/.ppt/.xls):需 LibreOffice 预转换,评估中

  • 图像文件(PNG/JPG)直接脱敏:OCR + 像素涂黑管线已具备,待封装

  • .docx 内嵌对象(OLE)与图表 XML 泄露面深化

License

AGPL-3.0-or-later(PyMuPDF 执行层传染)。检测层与审计思路可参考实现。

Available Tools

7 tools
extract_imageA

从 PDF 提取指定嵌入图像保存为 PNG(用于制作 logo 脱敏模板:先 redact_scan 拿到图像 xref 清单,再提取可疑 logo 作为模板)。

Inputs: xref (required), pdf_path (required), output_path (required).

glossary_addA

把确认过的敏感词沉淀进词典,后续 scan 自动生效。

Inputs: terms (required).

glossary_listA

查看持久化敏感词词典(scan 时自动并入候选)。

Inputs: no named parameters. Returns: result

glossary_removeC

从词典移除词条。

Inputs: terms (required).

redact_applyA

执行脱敏(真删除,不可恢复)。terms 必须是已确认的敏感词清单——请先调用 redact_scan 并经用户确认后再调用本工具。logo_templates 仅支持 PDF。

Inputs: terms (required), input_path (required), output_path (required), logo_templates.

redact_auditA

取证级审计:对象流/文本层/元数据/修订记录/批注/OCR 逐面检查,判定敏感词 是否彻底移除。交付脱敏文件前必须通过本审计。

Inputs: terms (required), doc_path (required), logo_templates.

redact_scanA

非破坏性扫描文档(不改文件),发现候选敏感项。支持 PDF(文字/扫描件自动 OCR)、DOCX、XLSX、PPTX、TXT/MD/CSV 等。返回候选清单(词条/来源/位置/次数)、 元数据泄露、格式相关清单。enable_ner 需 zh_core_web_trf 模型;标准/公文类 文档建议关闭(噪声大)。

Inputs: input_path (required), keywords, enable_ner, ner_labels, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: scanning, applying, auditing, glossary management, and image extraction. Even redact_scan and redact_audit are sharply differentiated as pre-redaction candidate discovery versus post-redaction forensic verification.

    Naming Consistency4/5

    Most tools follow a clear domain-prefix pattern: redact_* for document operations and glossary_* for dictionary operations. The exception is extract_image, which uses verb+noun ordering rather than prefix+operation, creating a minor but noticeable inconsistency.

    Tool Count5/5

    Seven tools is well-scoped for a document redaction server. Each tool fills a necessary role in the workflow without redundancy or bloat, and the count supports a complete redaction pipeline.

    Completeness5/5

    The toolkit covers the full redaction lifecycle: scan for candidates, apply redaction, audit the result, and persist confirmed terms in a glossary. Supporting image extraction and glossary management fills the surrounding workflow needs, leaving no obvious dead ends.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      An MCP server that redacts PII/PHI from text before it ever reaches an LLM — self-hosted, fail-closed, and HIPAA-aware.
      3
      21 PyPI
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that enables AI agents to redact text, metadata, annotations, and image areas in documents using GroupDocs.Redaction, with support for various document formats and easy integration with Claude, Cursor, and GitHub Copilot.
      MIT
    • F
      license
      A
      quality
      B
      maintenance
      MCP server for local, verifiable PDF redaction. Enables AI agents to find sensitive regions, locate text, redact PDFs on-device, verify redaction and tamper-evidence seals, and generate PDFs—without uploading confidential documents.
      8
      365 npm
      -