rhoso-accel-mcp
rhoso-accel-mcp
一个单一的 MCP 服务器,让 AI 代理能够端到端驱动完整的 RHOSO 到 GPU 验证虚拟机启动流程
封装了 rhos-vaf/dev-tools —— 其 make 目标被
暴露为 MCP 工具 —— 遵循 Red Hat
template-mcp-server 的约定。
工具
读取/安全(自动运行):
工具 | 封装 |
|
|
|
|
|
|
写入/破坏性(需要 confirm=True):
工具 | 封装 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
每个工具都返回 {"status", "command", "stdout", "stderr", "exit_code"},并且从不抛出异常。
配置
DEVTOOLS_DIR(在 .env 中)指向你的 dev-tools 检出目录。如果留空,服务器会在
首次使用时自动克隆 rhos-vaf/dev-tools 到 DEVTOOLS_CLONE_DIR(/tmp/dev-tools),并在
后续运行时刷新它(git remote update && git checkout origin/main)—— 因此只读工具在
零配置下即可工作。对于真实部署,请将 DEVTOOLS_DIR 设置为包含
configs/sno.local.sh 的自己的检出目录;自动克隆没有配置,因此在提供配置之前,
破坏性工具将无法通过 validate_config。
运行
cp .env.example .env # optionally set DEVTOOLS_DIR
make install # uv venv + deps
make test # unit tests (no real make execution)
make local # run over stdio (local agent)
# make http # run over HTTP (remote/CI agent)向 MCP 客户端注册,例如通过 stdio 使用 Claude CLI:
claude mcp add rhoso-accel --scope user -- uv run --directory /path/to/rhoso-accel-mcp rhoso-accel-mcp或通过 HTTP:
make http # serves on http://127.0.0.1:5001
claude mcp add --transport http rhoso-accel http://localhost:5001/mcp --scope userThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server exposing the Backtest360 engine API as tools for AI agents.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for generating rough-draft project plans from natural-language prompts.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MiguelCarpio/rhoso-accel-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server