Copr MCP
Provides tools to interact with Fedora Copr, enabling users to manage projects, builds, and packages through natural language.
README
Copr MCP
Demo
Please see the First look at the Copr MCP server.
Prerequisites
Install dependencies
uv sync
MCP Usage
Register the MCP server with Claude Code, Codex, Cursor, or any other agent.
Claude Code
To register the copr server with Claude Code, execute this command
$ claude mcp add copr --scope user \
-- uv run --directory "$(pwd)" python main.py
If you don't need this MCP server anymore, uninstall it.
$ claude mcp remove copr
Codex
$ codex mcp add copr -- uv run --directory "$(pwd)" python main.py
If you don't need this MCP server anymore, uninstall it.
$ codex mcp remove copr
Cursor
If you use Cursor, open or create ~/.cursor/mcp.json and add the copr
entry to the list of mcpServers.
Change the directory (~/src/copr-mcp) to wherever you've cloned this
copr-mcp project.
{
"mcpServers": {
"copr": {
"command": "uv",
"args": [
"run",
"--directory",
"~/src/copr-mcp",
"python",
"main.py"
]
}
}
}
If you don't need this MCP server anymore, removing the copr
entry from the mcpServers list in ~/.cursor/mcp.json.
Run tools
Once the MCP server is registered, go to i.e. Claude or Cursor and ask it questions like
Tell me the status of Copr build 8101723
Can you give me last 5 builds from the frostyx/foo Copr project?
Build the DistGit package hello in my frostyx/foo project
Create a Copr project frostyx/foo with a fedora-43-x86_64 chroot
Development
Go to https://console.anthropic.com, "API Keys" and generate a new key. Then export it in your terminal:
$ export ANTHROPIC_API_KEY=...
Then run
$ uv run main.py --prompt "Tell me the status of Copr build 8101723"
To use a different model pass --model
$ uv run main.py --model gpt-5-mini --prompt "Tell me the status of Copr build 8101723"
Full list of models can be found here: https://pydantic.dev/docs/ai/api/models/base/#pydantic_ai.models.KnownModelName
Tests
$ uv run mypy .
$ uv run ruff check
$ uv run pytest
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
