tchMaterial-parser-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tchMaterial-parser-mcp帮我搜索高中物理教材并下载PDF"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tchMaterial-parser-mcp
为 happycola233/tchMaterial-parser 提供 MCP(Model Context Protocol)适配层,使 AI 客户端可以调用教材搜索、解析与下载等能力。
本项目采用 wrapper repository + Git submodule 结构。上游 tchMaterial-parser 保持独立,不把 MCP 逻辑侵入上游源码。
目录
tchMaterial-parser-mcp/
├── upstream/
│ └── tchMaterial-parser/ # 官方仓库 Git submodule
├── src/
│ └── tchmaterial_parser_mcp/
│ ├── adapters.py # 上游兼容边界
│ ├── schemas.py # MCP 稳定数据结构
│ ├── tools.py # MCP tools
│ └── server.py # MCP server
├── tests/
├── docs/
└── scripts/Related MCP server: Moodle MCP Server
克隆
git clone --recurse-submodules <this-repository-url>
cd tchMaterial-parser-mcp如果已经普通 clone:
git submodule update --init --recursive初始化
./scripts/setup.sh脚本会初始化 submodule、创建 .venv、安装 MCP SDK 和本项目,并运行测试。 同时会以 editable 模式安装当前 submodule,因此 MCP 使用的就是外层仓库固定的上游 commit。
启动本地 stdio MCP Server:
./scripts/run-mcp.sh该命令正常启动后不会打印业务输出,而是等待 MCP Host 通过 stdin/stdout 通信。
运行不下载文件的在线冒烟测试:
./scripts/smoke-live.sh上游更新
./scripts/update-upstream.sh脚本会把 submodule 更新到官方 main 最新提交,然后运行上游兼容性测试。外层仓库最终只记录新的 submodule commit 指针。
下载目录
默认下载到:
~/Downloads/tchMaterial-parser可以通过环境变量修改:
TCHMATERIAL_MCP_DOWNLOAD_DIR=/path/to/materialsdownload_material 不接受任意输出目录参数,避免模型把文件写到未授权的系统位置。
Codex
本地 stdio 启动命令为:
/home/cislunar/App/tchMaterial-parser-mcp/scripts/run-mcp.sh推荐给下载 tool 配置较长超时时间,因为大体积 PDF 可能超过普通 MCP tool 的默认超时。
详细约束见:
docs/architecture.md
docs/upstream-maintenance.md
docs/mcp-tools.md
THIRD_PARTY_NOTICES.md
当前状态
第一版已提供 search_materials、get_material、resolve_material、download_material 四个 MCP Tool,并使用官方 MCP Python SDK v2 的 stdio transport。download_material 默认只下载 PDF;如果教材还包含 MP3 等关联资源,推荐先由 resolve_material 检查并询问用户是否需要一起下载,用户未特别要求时仍保持 PDF-only。
This server cannot be deployed
Maintenance
Related MCP Connectors
Read-only MCP server exposing a user ORANO library to their own AI agent.
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA lightweight, stdio-based MCP server enabling AI assistants to perform local file system operations like reading, writing, searching, and executing commands.2,323 npmMIT
- AlicenseNot gradedqualityDmaintenanceA powerful Model Context Protocol (MCP) server that seamlessly integrates AI assistants with Moodle Learning Management System. Enable your AI assistant to access courses, retrieve educational content, download resources, and search through your learning materials.27 npmMIT
- AlicenseNot gradedqualityCmaintenanceA provider-neutral Web Search MCP server and CLI that combines live search, scholarly discovery, verified PDF downloads, URL normalization, multi-provider ranking, secure page fetching, caching, and citation-ready research evidence.MIT
- FlicenseBqualityCmaintenanceProvides a minimal MCP server with safe tools for AI assistants to search project files, read files, search local documentation, and run pre-approved checks within a single project directory.4-