What environment variables are required?
Three variables are mandatory: `MCP_GOVBOX_PROJECT_PATH` (path to the Govbox project), `MCP_SHELL_PATH` (e.g., `/bin/zsh`), and `MCP_SHELL_OPTIONS` (additional shell arguments, e.g., `-c`).
@giovanoh
基本信息
Protótipo de servidor MCP em Go para utilização com LLMs na automatização de processos internos em Ruby/rake
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-govbox": {
"command": "docker",
"args": [
"build",
"-t",
"mcp-server-govbox",
"."
]
}
}
}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。
MCP Server Govbox is a Model Context Protocol server that bridges large language models (LLMs) with Rake tasks from the Govbox project. It lets LLMs execute Rakefile commands safely and programmatically, without requiring knowledge of specific Rake commands.
Clone the repository, build using Docker (docker build -t mcp-server-govbox .) or Go (go build cmd/app/main.go), then configure the required environment variables (MCP_GOVBOX_PROJECT_PATH, MCP_SHELL_PATH, MCP_SHELL_OPTIONS) in a .env file placed in the client’s root folder. Finally, set up the MCP client (e.g., Claude Desktop) by adding the server configuration to its claude_desktop_config.json.
Three variables are mandatory: `MCP_GOVBOX_PROJECT_PATH` (path to the Govbox project), `MCP_SHELL_PATH` (e.g., `/bin/zsh`), and `MCP_SHELL_OPTIONS` (additional shell arguments, e.g., `-c`).
The `.env` file must be located in the root folder of the client that calls the server. For Claude Desktop on Windows, the path is `C:\Users\<User>\AppData\Local\AnthropicClaude\app-<Version>\.env`.
The `.env` file is missing, has permission issues, or is malformed. Ensure it exists in the correct location and is properly formatted.
One or more required environment variables are missing, empty, or point to a nonexistent shell. Check that `MCP_GOVBOX_PROJECT_PATH`, `MCP_SHELL_PATH`, and `MCP_SHELL_OPTIONS` are correctly set.
Verify that all environment variables are correct, the `.env` file is in place, the user has read/execute permissions for the shell and project directory, and the shell path points to an existing executable. Check server logs for details.
Hindsight: Agent Memory That Learns

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
A curated list of references for MLOps
🚀 The fast, Pythonic way to build MCP servers and clients.
评论