FullScope-MCP: 内容总结运营 MCP Server,支持网页抓取、文件读取、内容总结、主题汇总等功能
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":"fullscope-mcp-server","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.
# FullScope-MCP > 内容总结运营 MCP Server,支持网页抓取、文件读取、内容总结、主题汇总等功能 <a href="https://glama.ai/mcp/servers/@yzfly/fullscope-mcp-server"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@yzfly/fullscope-mcp-server/badge" alt="FullScope-MCP MCP server" /> </a> ## 🌟 功能特性 FullScope-MCP 是一个功能全面的 Model Context Protocol (MCP) 服务器,专门用于内容总结和运营场景。支持以下核心功能: 1. **🤖 模型调用**: 直接调用大语言模型进行回答 2. **🌐 网页抓取**: 抓取网页内容,可选保存为 txt 文本文件 3. **📝 内容总结**: 将任意内容总结为指定长度(默认原来的 20%,脱水版) 4. **🔗 网页总结**: 获取网页内容并自动总结为精炼版本 5. **📄 文本文件总结**: 读取 txt 等格式的文本文件并总结内容(限制返回 2k 字符) 6. **📚 PDF 文件总结**: 读取 PDF 文件并总结文本内容(限制返回 2k 字符) 7. **🎯 主题汇总**: 类似 RAG 功能,给定资料内容和查询主题,返回最相关的内容总结(2k 字符内) ## 📦 安装 ### 使用 uvx 安装(推荐) ```bash uvx fullscope-mcp-server ``` ### 使用 pip 安装 ```bash pip install fullscope-mcp-server ``` ### 从源码安装 ```bash git clone https://github.com/yzfly/fullscope-mcp cd fullscope-mcp pip install -e . ``` ## ⚙️ 配置 ### 环境变量配置 在使用之前,需要配置以下环境变量: #### 必需配置 ```bash # MiniMax API Key(必需) export OPENAI_API_KEY="your-minimax-api-key" ``` #### 可选配置 ```bash # API 基础 URL(默认使用 MiniMax) export OPENAI_BASE_URL="https://api.minimaxi.com/v1" # 使用的模型(默认 MiniMax-M1) export OPENAI_MODEL="MiniMax-M1" # 输入上下文最大 token 数(默认 120000) export MAX_INPUT_TOKENS="120000" # 输出上下文最大 token 数(默认 8000) export MAX_OUTPUT_TOKENS="8000" ``` ### Claude Desktop 配置 在 Claude Desktop 中使用时,请添加以下配置到 `claude_desktop_config.json`: ```json { "mcpServers": { "fullscope-mcp": { "command": "uvx", "args": ["fullscope-mcp-server"], "env": { "OPENAI_API_KEY": "your-minimax-api-key-here", "OPENAI_BASE_URL": "https://api.minimaxi.com/v1", "OPENAI_MODEL": "MiniMax-M1", "MAX_INPUT_TOKENS": "900000", "MAX_OUTPUT_TOKENS": "8000" } } } } ``` 或者使用 pip 安装版本: ```json { "mcpServers": { "fullscope-mcp": { "command": "python", "args": ["-m", "fullscope_mcp_server"], "env": { "OPENAI_API_KEY": "your-minimax-api-key-here", …
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.