{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_hkdkumyk5hte","handle":"paizhaojieti-stdio-mcp","url":"https://wellknown.network/agents/paizhaojieti-stdio-mcp","links":{"self":"https://wellknown.network/agents/paizhaojieti-stdio-mcp/record.json","html":"https://wellknown.network/agents/paizhaojieti-stdio-mcp","markdown":"https://wellknown.network/agents/paizhaojieti-stdio-mcp/record.md","api":"https://wellknown.network/api/v1/agents/paizhaojieti-stdio-mcp","status":"https://wellknown.network/api/v1/agents/paizhaojieti-stdio-mcp/status","claim":"https://wellknown.network/agents/paizhaojieti-stdio-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/paizhaojieti-stdio-mcp/claim.json","badge":"https://wellknown.network/agents/paizhaojieti-stdio-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/paizhaojieti-stdio-mcp/history","tools":"https://wellknown.network/api/v1/agents/paizhaojieti-stdio-mcp/tools"},"ard":{"identifier":"urn:air::server:paizhaojieti-stdio-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"paizhaojieti-stdio-mcp","summary":"基于智谱AI拍照解题智能体的STDIO类型MCP服务","description":"# Paizhaojieti STDIO MCP Server\n\n基于智谱AI拍照解题智能体的STDIO类型MCP服务，支持在ModelScope上使用个人授权的阿里云函数计算资源进行部署。\n\n## 功能特点\n\n- 📸 **拍照解题**: 支持数学题、物理题、化学题等各种学科的题目识别和解答\n- 🔄 **STDIO协议**: 符合ModelScope MCP STDIO协议规范\n- ☁️ **云原生部署**: 支持在ModelScope上使用个人阿里云函数计算资源部署\n- 🚀 **快速响应**: 基于智谱AI拍照解题智能体，响应速度快\n- 📦 **轻量级**: 仅依赖requests库，部署简单\n- 🧪 **易于测试**: 提供完整的测试脚本\n\n## 技术栈\n\n- Python 3.7+\n- requests库\n- ModelScope MCP STDIO协议\n\n## 快速开始\n\n### 本地开发环境\n\n#### 安装依赖\n\n```bash\npip install -r requirements.txt\n```\n\n#### 运行测试\n\n```bash\n# 运行测试脚本\npython test_client.py\n```\n\n测试脚本会自动启动服务，测试所有功能，并输出详细结果。\n\n#### 直接运行服务\n\n```bash\npython server.py\n```\n\n服务启动后，会从标准输入读取JSON-RPC请求，处理后写入标准输出。\n\n## 部署到ModelScope\n\n### 步骤1: 准备GitHub仓库\n\n1. 创建GitHub仓库，命名为 `paizhaojieti_stdio_mcp`\n2. 上传代码到仓库\n\n```bash\ngit init\ngit add .\ngit commit -m \"Initial commit\"\ngit remote add origin https://github.com/yourusername/paizhaojieti_stdio_mcp.git\ngit push -u origin main\n```\n\n### 步骤2: 在ModelScope创建MCP服务\n\n1. 访问 [ModelScope MCP广场](https://modelscope.cn/mcp)\n2. 点击\"创建MCP服务\"或\"发布MCP服务\"\n3. 填写基本信息：\n   - **MCP名称**: Paizhaojieti STDIO MCP Server\n   - **MCP描述**: 基于智谱AI拍照解题智能体的STDIO类型MCP服务\n   - **MCP类型**: STDIO\n   - **GitHub仓库**: https://github.com/yourusername/paizhaojieti_stdio_mcp\n   - **部署方式**: 选择\"个人阿里云函数计算资源\"\n   - **配置文件路径**: mcp_config.json\n4. 点击\"提交\"完成创建\n\n### 步骤3: 验证部署\n\n1. 在ModelScope MCP广场搜索并找到你的服务\n2. 点击\"调用\"按钮\n3. 填写测试参数：\n   - `image_url`: 题目图片URL\n   - `api_key`: 智谱AI API密钥\n4. 点击\"执行\"查看结果\n\n## 使用说明\n\n### 支持的工具\n\n#### solve_image_problem\n\n**功能**: 通过上传图片URL来解题，支持数学题、物理题、化学题等各种学科的题目识别和解答。\n\n**参数**:\n- `image_url` (必填): 题目图片的URL地址，必须是公网可访问的图片链接\n- `api_key` (必填): 智谱AI的API密钥，用于调用拍照解题智能体\n\n**响应示例**:\n\n```json\n{\n  \"jsonrpc\": \"2.0\",\n  \"id\": 1,\n  \"result\": {\n    \"content\": [\n      {\n        \"type\": \"text\",\n        \"text\": \"1.大语言模型基于 Transformer 架构延伸出不同的路线图，BERT 属于其中哪一种路线图？\\nA. Encoder-Only\\nB. Decoder-Only\\nC. Encoder-decoder\\nD. 以上都不是\\n【解析】\\n本题考查对大语言模型架构的理解。BERT（Bidirectional Encoder Representations from Transformers）是Google在2018年发布的一种预训练语言模型，它基于Transformer架构，但与传统的Transformer不同，BER…","publisher":{"name":"Yutian","url":null},"homepage":"https://github.com/La0bALanG/paizhaojieti_stdio_mcp","repository":"https://github.com/La0bALanG/paizhaojieti_stdio_mcp","version":"1.0.0","license":"MIT","protocols":["mcp"],"tags":["mcp","stdio","ai","image-recognition","problem-solving"],"pricing":null,"endpoints":[{"url":"pypi:paizhaojieti-stdio-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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-understanding","name":"Image Understanding","confidence":0.75,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev","media"],"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":"paizhaojieti-stdio-mcp","registry":"pypi","observedAt":"2026-10-22T17:24:46.897Z","publishedAt":"2026-01-09T08:39:50.356394Z","latestVersion":"1.0.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"paizhaojieti-stdio-mcp","url":"https://pypi.org/project/paizhaojieti-stdio-mcp/","firstSeenAt":"2026-09-10T09:25:23.700Z","fetchedAt":"2026-10-22T17:22:52.014Z","normalizedAt":"2026-10-22T17:22:52.014Z"}]},"firstSeenAt":"2026-09-10T09:25:23.700Z","updatedAt":"2026-10-22T17:24:46.897Z"}