{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_43em6wbtx3pd","handle":"pdf-tools-mcp","url":"https://wellknown.network/agents/pdf-tools-mcp","links":{"self":"https://wellknown.network/agents/pdf-tools-mcp/record.json","html":"https://wellknown.network/agents/pdf-tools-mcp","markdown":"https://wellknown.network/agents/pdf-tools-mcp/record.md","api":"https://wellknown.network/api/v1/agents/pdf-tools-mcp","status":"https://wellknown.network/api/v1/agents/pdf-tools-mcp/status","claim":"https://wellknown.network/agents/pdf-tools-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/pdf-tools-mcp/claim.json","badge":"https://wellknown.network/agents/pdf-tools-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/pdf-tools-mcp/history","tools":"https://wellknown.network/api/v1/agents/pdf-tools-mcp/tools"},"ard":{"identifier":"urn:air::server:pdf-tools-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"pdf-tools-mcp","summary":"A FastMCP-based PDF reading and manipulation tool server","description":"# PDF Tools MCP Server\n\n[English](#english) | [中文](#中文)\n\n---\n\n## 中文\n\n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。\n\n### 功能特性\n\n- 📄 读取 PDF 文件指定页面范围的内容\n- 🔢 支持起始和结束页面参数（包含范围）\n- 🛡️ 自动处理无效页码（负数、超出范围等）\n- 📊 获取 PDF 文件的基本信息\n- 🔗 合并多个 PDF 文件\n- ✂️ 提取 PDF 的特定页面\n- 🔍 正则表达式搜索功能，支持分页查看结果\n- 🌐 **URL 支持** - 支持直接从 URL 读取和操作 PDF 文件\n- 💾 智能缓存机制，相同 URL 的 PDF 自动复用临时文件\n\n### 安装\n\n#### 从 PyPI 安装\n\n```bash\nuv add pdf-tools-mcp\n```\n\n如果 `uv add` 遇到依赖冲突，建议使用：\n\n```bash\nuvx tool install pdf-tools-mcp\n```\n\n#### 从源码安装\n\n```bash\ngit clone https://github.com/yourusername/pdf-tools-mcp.git\ncd pdf-tools-mcp\nuv sync\n```\n\n### 使用方法\n\n#### 与 Claude Desktop 集成\n\n添加到你的 `~/.config/claude/claude_desktop_config.json` (Linux/Windows) 或 `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS):\n\n**开发/未发布版本配置**\n\n```json\n{\n  \"mcpServers\": {\n    \"pdf-tools-mcp\": {\n      \"command\": \"uv\",\n      \"args\": [\n        \"--directory\",\n        \"<path/to/the/repo>/pdf-tools-mcp\",\n        \"run\",\n        \"pdf-tools-mcp\",\n        \"--workspace_path\",\n        \"</your/workspace/directory>\",\n        \"--tempfile_dir\",\n        \"</your/temp/directory>\"\n      ]\n    }\n  }\n}\n```\n\n**已发布版本配置**\n\n```json\n{\n  \"mcpServers\": {\n    \"pdf-tools-mcp\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"pdf-tools-mcp\",\n        \"--workspace_path\",\n        \"</your/workspace/directory>\",\n        \"--tempfile_dir\",\n        \"</your/temp/directory>\"\n      ]\n    }\n  }\n}\n```\n\n**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。\n\n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。\n\n#### 作为命令行工具\n\n```bash\n# 基本使用\npdf-tools-mcp\n\n# 指定工作目录和临时文件目录\npdf-tools-mcp --workspace_path /path/to/workspace --tempfile_dir /path/to/temp\n```\n\n#### 作为 Python 包\n\n```python\nfrom pdf_tools_mcp import read_pdf_pages, get_pdf_info, merge_pdfs, extract_pdf_pages\n\n# 读取 PDF 页面（支持 URL）\nresult = await read_pdf_pages(\"https://example.com/document.pdf\", 1, 5)\n\n# 获取 PDF 信息（支持 URL）\ninfo = await get_pdf_info(\"document.pdf\")\n\n# 合并 PDF 文件（支持 URL 和本地文件混合）\nresult = awa…","publisher":null,"homepage":"https://github.com/lockon-n/pdf-tools-mcp#readme","repository":"https://github.com/lockon-n/pdf-tools-mcp#readme","version":"0.1.4","license":"MIT","protocols":["mcp"],"tags":["fastmcp","mcp","pdf","pdf-manipulation","text-extraction"],"pricing":null,"endpoints":[{"url":"pypi:pdf-tools-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":0.713,"provenance":"derived"}],"categories":["dev","documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"pdf-tools-mcp","registry":"pypi","observedAt":"2026-10-28T19:22:49.637Z","publishedAt":"2025-08-10T17:21:33.123101Z","latestVersion":"0.1.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"pdf-tools-mcp","url":"https://pypi.org/project/pdf-tools-mcp/","firstSeenAt":"2026-09-10T09:25:56.522Z","fetchedAt":"2026-10-28T19:21:45.491Z","normalizedAt":"2026-10-28T19:21:45.491Z"}]},"firstSeenAt":"2026-09-10T09:25:56.522Z","updatedAt":"2026-10-28T19:22:49.637Z"}