file-analysis
File Analysis MCP
一个读取特定文件夹中的非结构化文档(PDF、DOCX、PPTX、SVG、PNG、JPG)并提取其结构/内容的个人用 MCP 服务器。 摘要由调用此服务器的 Claude Code/Codex 的 LLM 完成,而非此服务器本身。 该服务器仅负责 文本/图像提取和文件夹结构识别。
准备工作
1. Python
python、pip 必须能正常运行。如果在 Windows 上 python 弹出 Microsoft Store 安装提示,
请确认以下事项:
从 python.org 安装 Python 3.11 或更高版本(64-bit),安装过程中 勾选 "Add python.exe to PATH"。
如果
python仍然指向 Store 存根:在 设置 → 应用 → 高级应用设置 → 应用执行别名 中 关闭 App Installer 的 python.exe/python3.exe 项。
2. Tesseract-OCR (PNG 的 OCR 功能所需,可选)
使用 UB-Mannheim Tesseract installer 安装后,
将 .mcp.json 中的 TESSERACT_CMD 值设置为实际安装路径。即使不安装,服务器也能正常运行;
分析 PNG 时会返回图像本身(多模态),仅 OCR 文本会被替换为 "unavailable" 消息。
Related MCP server: ReadPDFx - OCR PDF MCP Server
安装
cd C:\Users\20229\Desktop\MCP
python -m venv .venv
.venv\Scripts\pip install -r requirements.txt验证
# 1. 샘플 파일 생성 (pdf/docx/pptx/svg/png/txt 각 1개)
.venv\Scripts\python scripts\generate_fixtures.py
# 2. MCP 없이 extractor만 직접 테스트
.venv\Scripts\python scripts\smoke_test.pyClaude Code 注册
此文件夹中的 .mcp.json 已经以项目作用域注册了该服务器。确认 command 路径与实际
.venv\Scripts\python.exe 位置一致后,重启 Claude Code,或使用 /mcp 命令
检查 file-analysis 服务器是否处于 connected 状态。
提供的工具
scan_folder(folder_path, max_depth=3, max_files=200):仅返回文件夹树和按扩展名统计的文件数量 (不读取内容)。analyze_file(file_path, max_chars=None):按扩展名提取单个文件。pdf/docx/pptx/svg → 文本/结构信息
png/jpg/jpeg → 图像(多模态) + OCR 文本
限制
SVG 仅解析 XML 结构(文本节点、图形数量、viewBox)。不含文本的纯矢量图 无法从视觉上得知其绘制内容 — 如有需要,请转换为 PNG 后重新分析。
提取量设有上限:PDF 50页/5万字,PPTX 100张幻灯片/5万字,PNG OCR 2万字等。 超过上限时,结果中会包含
truncated: true和提示信息。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables reading and processing various document formats including Word, PDF, RTF, and text files. Supports extracting media elements like images and links, with features for PDF page range selection and automatic text encoding detection.8MIT
- AlicenseNot gradedqualityDmaintenanceProvides intelligent OCR and PDF processing capabilities that automatically detect whether PDFs contain digital text or scanned images and apply appropriate extraction methods. Supports text extraction, OCR processing, structure analysis, and batch operations.MIT
- AlicenseNot gradedqualityFmaintenanceEnables PDF document processing including text, image, and table extraction, as well as intelligent classification and similarity analysis across multiple languages.49MIT
- FlicenseNot gradedqualityCmaintenanceEnables local, read-only extraction of text and structure from PDF, DOCX, PPTX, SVG, and PNG files, including OCR for images, directory tree and metadata reporting, with strict path isolation and audit logging.
Related MCP Connectors
Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Tag, rename, and enrich PDFs and images. Free tier: 1,500 tags/month, no credit card.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/JAEJOONYOO/YJJ_MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server