{"id":46666048,"url":"https://github.com/codeeagle/markitdown","last_synced_at":"2026-03-11T01:01:02.111Z","repository":{"id":343051358,"uuid":"1176120843","full_name":"CodeEagle/markitdown","owner":"CodeEagle","description":null,"archived":false,"fork":false,"pushed_at":"2026-03-08T17:09:15.000Z","size":20,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-08T19:57:30.991Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CodeEagle.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-08T16:41:10.000Z","updated_at":"2026-03-08T17:09:18.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/CodeEagle/markitdown","commit_stats":null,"previous_names":["codeeagle/markitdown"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/CodeEagle/markitdown","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeEagle%2Fmarkitdown","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeEagle%2Fmarkitdown/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeEagle%2Fmarkitdown/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeEagle%2Fmarkitdown/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CodeEagle","download_url":"https://codeload.github.com/CodeEagle/markitdown/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeEagle%2Fmarkitdown/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30364569,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T21:41:54.280Z","status":"ssl_error","status_checked_at":"2026-03-10T21:40:59.357Z","response_time":106,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-03-08T18:05:08.456Z","updated_at":"2026-03-11T01:01:02.084Z","avatar_url":"https://github.com/CodeEagle.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MarkItDown Web + MCP 懒猫微服\n\n[MarkItDown](https://github.com/microsoft/markitdown) 是 Microsoft 维护的文件与 URL 转 Markdown 工具。本仓库将它移植到懒猫微服，同时提供可直接在浏览器中使用的 Web 转换界面，以及可接入 MCP 客户端的 Streamable HTTP 与 SSE 入口。\n\n## 上游项目\n\n- 上游仓库: https://github.com/microsoft/markitdown\n- 上游主页: https://github.com/microsoft/markitdown\n- 上游许可证: MIT\n- 当前适配版本:\n  - `source_version`: `v0.1.5`\n  - `build_version`: `0.1.5`\n\n## 应用说明\n\n迁移后的应用同时启动两个服务：\n\n- Web API: `lazycat-markitdown web --host 0.0.0.0 --port 3000`\n- MCP 服务: `lazycat-markitdown mcp --http --host 0.0.0.0 --port 3001`\n\n对外提供以下入口：\n\n- 首页: `https://\u003c你的应用域名\u003e/`\n- Web 转换 API: `https://\u003c你的应用域名\u003e/api/convert`\n- MCP Streamable HTTP: `https://\u003c你的应用域名\u003e/mcp`\n- MCP SSE: `https://\u003c你的应用域名\u003e/sse`\n- SSE 消息通道: `https://\u003c你的应用域名\u003e/messages/`\n\n首页提供浏览器可直接使用的 URL 转换与文件上传界面，不再只是静态说明页。\n内部健康探针走 `markitdown-web` 的 `/healthz`。\n\n## 功能特性\n\n- 将 `http:`、`https:`、`file:`、`data:` URI 转换为 Markdown\n- 内置 `markitdown[all]` 依赖，覆盖 PDF、Office、图片、音频等常见格式\n- 浏览器直接上传文件或输入 URL，返回 Markdown 文本\n- 支持 Streamable HTTP 与 SSE 两种 MCP 传输方式\n- 提供持久化工作目录，便于通过 `file:///workdir/...` 访问本地文件\n\n## 环境变量\n\n| 变量名 | 默认值 | 说明 |\n| --- | --- | --- |\n| `MARKITDOWN_ENABLE_PLUGINS` | `true` | 启用 MarkItDown 插件加载 |\n| `MARKITDOWN_MAX_UPLOAD_BYTES` | `26214400` | Web 上传大小限制，单位字节，默认 25 MB |\n\n## 数据目录\n\n应用将懒猫持久化目录映射为容器内工作目录：\n\n| 懒猫目录 | 容器内路径 | 用途 |\n| --- | --- | --- |\n| `/lzcapp/var/data` | `/workdir` | 存放待转换文件，供 `file:///workdir/...` URI 访问 |\n\n示例：如果你把文件写入 `/lzcapp/var/data/report.pdf`，则 MCP 调用时可传入 `file:///workdir/report.pdf`。\n\n## 使用方式\n\n### 1. 浏览器使用 Web 转换\n\n访问应用根路径 `/`，可以：\n\n- 输入远程 URL 并直接转换\n- 上传本地文件并直接转换\n- 复制或下载转换后的 Markdown 结果\n\n也可以直接请求 Web API：\n\n```bash\ncurl -X POST \"https://\u003c你的应用域名\u003e/api/convert\" \\\n  -H \"content-type: application/json\" \\\n  -d '{\"uri\":\"https://example.com/report.pdf\"}'\n```\n\n上传文件：\n\n```bash\ncurl -X POST \"https://\u003c你的应用域名\u003e/api/convert?format=text\" \\\n  -F \"file=@./report.docx\"\n```\n\n### 2. 使用 MCP Inspector 调试\n\n将 Inspector 连接到：\n\n- Streamable HTTP: `https://\u003c你的应用域名\u003e/mcp`\n- SSE: `https://\u003c你的应用域名\u003e/sse`\n\n本地也可以直接运行仓库内脚本做最小 MCP 验证：\n\n```bash\npython3 scripts/test_mcp_local.py\n```\n\n测试线上服务：\n\n```bash\npython3 scripts/test_mcp_local.py \\\n  --endpoint https://\u003c你的应用域名\u003e/mcp \\\n  --insecure\n```\n\n### 3. 通过 MCP 转换远程文件\n\n通过 MCP 工具 `convert_to_markdown(uri)` 传入：\n\n- `https://example.com/file.pdf`\n- `file:///workdir/example.docx`\n- `data:application/pdf;base64,...`\n\n## 自动构建\n\n仓库包含兼容 `lzcat-trigger` 的 `.github/workflows/update-image.yml`。目标 workflow 只负责：\n\n1. 获取上游 `source_version`\n2. 构建包含 Web 与 MCP 双入口的镜像\n3. 推送 `ghcr.io/\u003cowner\u003e/markitdown:\u003csource_version\u003e`\n\n后续镜像复制到 `registry.lazycat.cloud`、manifest 回写、`.lpk` 构建与发布，默认由 `lzcat-trigger` 统一处理。\n\n## 相关链接\n\n- 上游 README: https://github.com/microsoft/markitdown#readme\n- `markitdown-mcp` 文档: https://github.com/microsoft/markitdown/tree/main/packages/markitdown-mcp\n- LazyCat 开发文档: https://developer.lazycat.cloud/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodeeagle%2Fmarkitdown","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodeeagle%2Fmarkitdown","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodeeagle%2Fmarkitdown/lists"}