@oras-project
基本信息
Discover artifacts across OCI-compliant registries with ease
工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
ORAS MCP Server enables registry-aware conversations in VS Code agent mode by exposing OCI registry operations through the Model Context Protocol. It is built with oras-go and does not require the separate oras CLI.
Configure the server in VS Code's .vscode/mcp.json to run either as a Docker container (ghcr.io/oras-project/oras-mcp:main serve) or from a downloaded binary (oras-mcp serve). On Linux with Docker, mount your Docker config file to share credentials; on macOS/Windows, use the released binary.
Add a server entry to `.vscode/mcp.json` with `"command": "docker"` and args `["run", "--rm", "-i", "ghcr.io/oras-project/oras-mcp:main", "serve"]`, or point to the extracted `oras-mcp` binary with `"command": "/path/to/oras-mcp"` and `"args": ["serve"]`.
For the released binary, run `oras login` or `docker login` on the host; the server picks up cached credentials automatically. For the Docker container on Linux, mount your Docker config file with inline `auths` entries. Helper-based configs are not supported in the container.
The server can run as a Docker container or as a standalone binary. The binary works on Linux, macOS, and Windows (download from GitHub releases). No ORAS CLI is required.
Yes, use the released binary instead of the Docker container because Docker Desktop on those platforms uses keychain helpers that cannot be mounted. Follow the binary setup instructions.
You can ask about image platforms, tags, signatures, and other OCI registry information. For example, "What platform does the image X support?" or "Does image Y have a signature?"
Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
A search tool helps dev to solve the naming things problem.
Open-source MCP to use Blender with any LLM
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
评论