Current collected state Current
Observed since 21 Oct, 10:13 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
ai-code-recorder-client
AI代码记录器 MCP 客户端 - 通过 MCP 协议记录 AI 生成的代码片段
AI代码记录器的 MCP 客户端,运行在本地,通过 MCP 协议与 Cursor 集成,获取 Git 信息并将 AI 生成的代码片段上报到远程服务器。
当前版本: v1.0.2
PyPI: ai-code-recorder-client
架构: 客户端本地运行 + 远程API服务器
从 PyPI 安装(推荐):
pip install ai-code-recorder-client
从源码安装(开发用):
# 克隆仓库并进入客户端目录
git clone https://github.com/ai-code-team/ai-code-recorder.git
cd ai-code-recorder/client
# 安装开发版本
pip install -e .
编辑 ~/.cursor/mcp.json(无则创建):
{
"mcpServers": {
"ai-code-recorder": {
"command": "uvx",
"args": ["ai-code-recorder-client"]
}
}
}
说明:
ai-code-recorder-client(pyproject.toml 的 project.scripts 中定义)AGENTS.md,给智能体提供使用规范project_root(可选)。不指定则使用当前工作目录project_root(必填):客户端项目的根目录绝对路径file_path(可选):文件的相对或绝对路径repository_info 与 user_infofilename、language、source、code(建议提供完整信息)file_path、project_context、repository_url、git_branch、commit_hash、meta本地开发:
git clone https://github.com/ai-code-team/ai-code-recorder.git
cd ai-code-recorder/client
pip install -e .
发布到 PyPI:
pip install build twine
export PYPI_API_TOKEN="pypi-your-token-here"
client/ 目录执行)./release.sh
发布脚本将执行:清理、构建、检查、安装测试与发布等步骤。
MIT License,详见仓库内 client/LICENSE。
Download counts and popularity will appear here as the collector receives them.
| Package / target | Requirement | Relationship |
|---|---|---|
fastmcpEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.8",
"evaluation": "NOT_EVALUATED"
} | fastmcp>=0.1.0 | runtime |
requestsEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.8",
"evaluation": "NOT_EVALUATED"
} | requests>=2.31.0 | runtime |
bdist_wheel · 10.03 KB · Python py3
sdist · 9.85 KB · Python source
Shared repository data · GitHub
Observed since 21 Oct, 10:13 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package_version:9a8180269b8a3098403e8faa285e7e2cc3a906e07a78ee238bf5acbd78f8877d