A FastMCP-based PDF reading and manipulation tool server
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"pdf-tools-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# PDF Tools MCP Server [English](#english) | [中文](#中文) --- ## 中文 一个基于 FastMCP 的 PDF 读取和操作工具服务器,支持从 PDF 文件的指定页面范围提取文本内容。 ### 功能特性 - 📄 读取 PDF 文件指定页面范围的内容 - 🔢 支持起始和结束页面参数(包含范围) - 🛡️ 自动处理无效页码(负数、超出范围等) - 📊 获取 PDF 文件的基本信息 - 🔗 合并多个 PDF 文件 - ✂️ 提取 PDF 的特定页面 - 🔍 正则表达式搜索功能,支持分页查看结果 - 🌐 **URL 支持** - 支持直接从 URL 读取和操作 PDF 文件 - 💾 智能缓存机制,相同 URL 的 PDF 自动复用临时文件 ### 安装 #### 从 PyPI 安装 ```bash uv add pdf-tools-mcp ``` 如果 `uv add` 遇到依赖冲突,建议使用: ```bash uvx tool install pdf-tools-mcp ``` #### 从源码安装 ```bash git clone https://github.com/yourusername/pdf-tools-mcp.git cd pdf-tools-mcp uv sync ``` ### 使用方法 #### 与 Claude Desktop 集成 添加到你的 `~/.config/claude/claude_desktop_config.json` (Linux/Windows) 或 `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS): **开发/未发布版本配置** ```json { "mcpServers": { "pdf-tools-mcp": { "command": "uv", "args": [ "--directory", "<path/to/the/repo>/pdf-tools-mcp", "run", "pdf-tools-mcp", "--workspace_path", "</your/workspace/directory>", "--tempfile_dir", "</your/temp/directory>" ] } } } ``` **已发布版本配置** ```json { "mcpServers": { "pdf-tools-mcp": { "command": "uvx", "args": [ "pdf-tools-mcp", "--workspace_path", "</your/workspace/directory>", "--tempfile_dir", "</your/temp/directory>" ] } } } ``` **注意**: 出于安全考虑,此工具只能访问指定工作目录(`--workspace_path`)内的文件,无法访问工作目录之外的文件。 如果配置后无法正常工作或在UI中无法显示,请通过 `uv cache clean` 清除缓存。 #### 作为命令行工具 ```bash # 基本使用 pdf-tools-mcp # 指定工作目录和临时文件目录 pdf-tools-mcp --workspace_path /path/to/workspace --tempfile_dir /path/to/temp ``` #### 作为 Python 包 ```python from pdf_tools_mcp import read_pdf_pages, get_pdf_info, merge_pdfs, extract_pdf_pages # 读取 PDF 页面(支持 URL) result = await read_pdf_pages("https://example.com/document.pdf", 1, 5) # 获取 PDF 信息(支持 URL) info = await get_pdf_info("document.pdf") # 合并 PDF 文件(支持 URL 和本地文件混合) result = awa…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.