{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_xk2k37x4zgys","handle":"mcp-server-okppt","url":"https://wellknown.network/agents/mcp-server-okppt","links":{"self":"https://wellknown.network/agents/mcp-server-okppt/record.json","html":"https://wellknown.network/agents/mcp-server-okppt","markdown":"https://wellknown.network/agents/mcp-server-okppt/record.md","api":"https://wellknown.network/api/v1/agents/mcp-server-okppt","status":"https://wellknown.network/api/v1/agents/mcp-server-okppt/status","claim":"https://wellknown.network/agents/mcp-server-okppt/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-server-okppt/claim.json","badge":"https://wellknown.network/agents/mcp-server-okppt/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-server-okppt/history","tools":"https://wellknown.network/api/v1/agents/mcp-server-okppt/tools"},"ard":{"identifier":"urn:air::server:mcp-server-okppt","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-server-okppt","summary":"A Python package to insert SVG images into PowerPoint presentations, with MCP server capabilities.","description":"# MCP OKPPT Server \n \n[![MCP Compatible](https://img.shields.io/badge/MCP-Compatible-blue)](https://github.com/anthropics/anthropic-tools) \n \n一个基于Model Context Protocol (MCP)的服务器工具，专门用于将SVG图像插入到PowerPoint演示文稿中。它能够保留SVG的矢量特性，确保在PowerPoint中显示的图像保持高品质和可缩放性。 \n \n## 设计理念 \n \n此项目是让大型语言模型（如Claude、GPT等）能够自主设计PowerPoint演示文稿的\"曲线救国\"解决方案。通过让AI生成SVG图像，再借助本工具将其全屏插入PPT幻灯片，我们成功实现了AI完全控制PPT设计的能力，而无需直接操作复杂的PPT对象模型。 \n \n这种方法带来三大核心优势： \n1. **AI完全控制**：充分发挥现代AI的图形设计能力，同时避开PPT编程的复杂性 \n2. **用户可编辑**：Office PowerPoint提供了强大的SVG编辑功能，插入后的SVG元素可以像原生PPT元素一样直接编辑、调整和重新着色，让用户能轻松地在AI生成基础上进行二次修改 \n3. **矢量级质量**：保持高品质可缩放的矢量特性，确保演示内容在任何尺寸下都清晰锐利 \n \n这一创新思路通过SVG作为AI与PPT之间的桥梁，既保证了设计的高度自由，又兼顾了最终成果的实用性和可维护性。 \n \n## 功能特点 \n \n- **矢量图保留**: 将SVG作为真实矢量图插入PPTX，保证高品质和可缩放性 \n- **批量批处理**: 支持一次操作多个SVG文件和幻灯片 \n- **全新演示文稿**: 直接从SVG文件创建完整的演示文稿 \n- **幻灯片复制与替换**: 智能复制SVG幻灯片并替换现有内容 \n- **SVG代码处理**: 支持直接从SVG代码创建文件 \n- **格式转换支持**: 内置SVG到PNG的转换功能 \n \n## 安装方法 \n \n### 方法一：从PyPI安装 \n \n```bash \n# 使用pip安装 \npip install mcp-server-okppt \n \n# 或使用uv安装 \nuv pip install mcp-server-okppt \n``` \n \n### 方法二：配置Claude Desktop \n \n在Claude Desktop配置文件中添加服务器配置： \n \n**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`   \n**Windows**: `%APPDATA%\\Claude\\claude_desktop_config.json` \n \n添加以下配置： \n \n```json \n{ \n  \"mcpServers\": { \n    \"okppt\": { \n      \"command\": \"uvx\", \n      \"args\": [ \n        \"mcp-server-okppt\" \n      ] \n    } \n  } \n} \n``` \n \n### 方法三：从源码安装并配置Cursor本地开发环境 \n \n在Cursor IDE中，可以通过本地配置文件来设置MCP服务器： \n \n**Windows**: `C:\\Users\\用户名\\.cursor\\mcp.json`   \n**macOS**: `~/.cursor/mcp.json` \n \n添加以下配置： \n \n```json \n{ \n  \"mcpServers\": { \n    \"okppt\": { \n      \"command\": \"uv\", \n      \"args\": [ \n        \"--directory\", \n        \"D:\\\\本地项目路径\\\\mcp-server-okppt\\\\src\\\\mcp_server_okppt\", \n        \"run\", \n        \"cli.py\" \n      ] \n    } \n  } \n} \n``` \n \n这种配置方式适合本地开发和测试使用，可以直接指向本地代码目录。 \n \n## 使用方法 \n \n### 使用Claude Desktop \n \n1. 安装并配置Claude Desktop \n2. 在配置文件中添加上述MCP服务器配置 \n3. 重启Claude Desktop \n4. 在对话中使用PPTX相关工具 \n \n### 使用MCP CLI进行开发 \n \n```bash \n# 运行测试 \nmcp test server.p…","publisher":null,"homepage":"https://github.com/NeekChaw/mcp-server-okppt","repository":"https://github.com/NeekChaw/mcp-server-okppt/issues","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mcp-server-okppt","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.presentations","name":"Presentations","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["dev","documents"],"language":"fr"},"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":"mcp-server-okppt","registry":"pypi","observedAt":"2026-10-22T11:30:46.911Z","publishedAt":"2025-06-08T07:58:37.646500Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-server-okppt","url":"https://pypi.org/project/mcp-server-okppt/","firstSeenAt":"2026-09-10T04:21:58.412Z","fetchedAt":"2026-10-22T11:28:34.974Z","normalizedAt":"2026-10-22T11:28:34.974Z"}]},"firstSeenAt":"2026-09-10T04:21:58.412Z","updatedAt":"2026-10-22T11:30:46.911Z"}