What dependencies are required to run this server?
You need JBang, a GitHub OAuth App, and an MCP client such as Claude Desktop.
@BarDweller
基本信息
A sandbox for MCP server prototyping
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ozzynet": {
"command": "cmd",
"args": [
"/c",
"C:\\Users\\YOURUSERNAME\\.jbang\\bin\\jbang.cmd",
"--quiet",
"org.ozzy:stiletto:1.0.0-SNAPSHOT:runner"
]
}
}
}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。
This is a prototype MCP server that offers tools but limits their access based on internal state. Users must authenticate via an external URL that uses Quarkus OIDC with GitHub OAuth. The resulting access token is stored per session ID.
Install JBang and create a GitHub OAuth App with the callback URL set to http://127.0.0.1:8080/auth. Copy the client ID and secret into application.properties. Then configure your MCP client (e.g., Claude Desktop) to run the JBang command jbang --quiet org.ozzy:stiletto:1.0.0-SNAPSHOT:runner. Authentication is initiated when a tool is used without a valid session.
localhost:8080)quarkusio/quarkus)You need JBang, a GitHub OAuth App, and an MCP client such as Claude Desktop.
Navigate to GitHub Developer Settings, create a new OAuth App, set the callback URL to `http://127.0.0.1:8080/auth`, then copy the client ID and generate a client secret. Paste both into `application.properties`.
When a tool is invoked without a valid session, the server returns a link like `http://127.0.0.1/auth?sessionId=<UUID>`. Clicking it redirects to GitHub for OAuth authorization. After successful authentication, you can retry the tool in Claude.
The README demonstrates two tools: `getSessionId` and `listIssues`. The `listIssues` tool requires authentication before use.
No, it is explicitly described as a prototype.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
评论