| Name | gemini-mcp JSON |
| Version |
0.2.7
JSON |
| download |
| home_page | None |
| Summary | MCP server for Gemini AI image processing - 基于 Gemini 2.5 Flash 的图片处理 MCP 服务 |
| upload_time | 2025-09-04 04:20:23 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | MIT |
| keywords |
ai
claude
gemini
image-processing
llm
mcp
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Gemini MCP
基于 Gemini 2.5 Flash 的图片处理 MCP 服务器，支持与 Claude Desktop、Cursor 等 MCP 客户端集成。
## 快速开始
### 使用 uvx 运行（推荐）
```bash
# 无需安装，直接运行
GEMINI_API_KEY=your-api-key uvx gemini-mcp
```
### 通过 pip 安装
```bash
pip install gemini-mcp
GEMINI_API_KEY=your-api-key gemini-mcp
```
## 配置客户端
### Claude Desktop
编辑 `~/Library/Application Support/Claude/claude_desktop_config.json`:
```json
{
"mcpServers": {
"gemini": {
"command": "uvx",
"args": ["gemini-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key"
}
}
}
}
```
### Cursor
编辑 `~/.cursor/mcp.json`:
```json
{
"mcpServers": {
"gemini": {
"command": "uvx",
"args": ["gemini-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key"
}
}
}
}
```
## 功能
- 🖼️ 支持本地文件、URL 和 Base64 图片
- 🚀 使用 uvx 无需安装即可运行
- 🔄 流式响应处理
- 📦 自动保存生成的图片
- 🌐 支持 SOCKS5 代理
## 使用示例
在 Claude Desktop 中：
```
分析这张图片：/path/to/image.jpg
描述 https://example.com/image.png 的内容
```
## 环境变量
- `GEMINI_API_KEY`: Gemini API 密钥（必需）
- `OUTPUT_DIR`: 输出目录（默认：`./outputs`）
- `ALL_PROXY`: SOCKS5 代理（如：`socks5://127.0.0.1:1080`）
## 命令行参数
```bash
gemini-mcp --help # 查看帮助
gemini-mcp --mode http # HTTP 模式
gemini-mcp --debug # 调试模式
```
## 许可证
MIT
Raw data
{
"_id": null,
"home_page": null,
"name": "gemini-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, claude, gemini, image-processing, llm, mcp",
"author": null,
"author_email": "Your Name <your.email@example.com>",
"download_url": "https://files.pythonhosted.org/packages/ea/c3/fe50e2e1b5e0fecf5a8aa127e3c5e69ca16f6ff8a498acad51e44e6b9875/gemini_mcp-0.2.7.tar.gz",
"platform": null,
"description": "# Gemini MCP\n\n\u57fa\u4e8e Gemini 2.5 Flash \u7684\u56fe\u7247\u5904\u7406 MCP \u670d\u52a1\u5668\uff0c\u652f\u6301\u4e0e Claude Desktop\u3001Cursor \u7b49 MCP \u5ba2\u6237\u7aef\u96c6\u6210\u3002\n\n## \u5feb\u901f\u5f00\u59cb\n\n### \u4f7f\u7528 uvx \u8fd0\u884c\uff08\u63a8\u8350\uff09\n\n```bash\n# \u65e0\u9700\u5b89\u88c5\uff0c\u76f4\u63a5\u8fd0\u884c\nGEMINI_API_KEY=your-api-key uvx gemini-mcp\n```\n\n### \u901a\u8fc7 pip \u5b89\u88c5\n\n```bash\npip install gemini-mcp\nGEMINI_API_KEY=your-api-key gemini-mcp\n```\n\n## \u914d\u7f6e\u5ba2\u6237\u7aef\n\n### Claude Desktop\n\n\u7f16\u8f91 `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n \"mcpServers\": {\n \"gemini\": {\n \"command\": \"uvx\",\n \"args\": [\"gemini-mcp\"],\n \"env\": {\n \"GEMINI_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n```\n\n### Cursor\n\n\u7f16\u8f91 `~/.cursor/mcp.json`:\n\n```json\n{\n \"mcpServers\": {\n \"gemini\": {\n \"command\": \"uvx\",\n \"args\": [\"gemini-mcp\"],\n \"env\": {\n \"GEMINI_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n```\n\n## \u529f\u80fd\n\n- \ud83d\uddbc\ufe0f \u652f\u6301\u672c\u5730\u6587\u4ef6\u3001URL \u548c Base64 \u56fe\u7247\n- \ud83d\ude80 \u4f7f\u7528 uvx \u65e0\u9700\u5b89\u88c5\u5373\u53ef\u8fd0\u884c\n- \ud83d\udd04 \u6d41\u5f0f\u54cd\u5e94\u5904\u7406\n- \ud83d\udce6 \u81ea\u52a8\u4fdd\u5b58\u751f\u6210\u7684\u56fe\u7247\n- \ud83c\udf10 \u652f\u6301 SOCKS5 \u4ee3\u7406\n\n## \u4f7f\u7528\u793a\u4f8b\n\n\u5728 Claude Desktop \u4e2d\uff1a\n\n```\n\u5206\u6790\u8fd9\u5f20\u56fe\u7247\uff1a/path/to/image.jpg\n\u63cf\u8ff0 https://example.com/image.png \u7684\u5185\u5bb9\n```\n\n## \u73af\u5883\u53d8\u91cf\n\n- `GEMINI_API_KEY`: Gemini API \u5bc6\u94a5\uff08\u5fc5\u9700\uff09\n- `OUTPUT_DIR`: \u8f93\u51fa\u76ee\u5f55\uff08\u9ed8\u8ba4\uff1a`./outputs`\uff09\n- `ALL_PROXY`: SOCKS5 \u4ee3\u7406\uff08\u5982\uff1a`socks5://127.0.0.1:1080`\uff09\n\n## \u547d\u4ee4\u884c\u53c2\u6570\n\n```bash\ngemini-mcp --help # \u67e5\u770b\u5e2e\u52a9\ngemini-mcp --mode http # HTTP \u6a21\u5f0f\ngemini-mcp --debug # \u8c03\u8bd5\u6a21\u5f0f\n```\n\n## \u8bb8\u53ef\u8bc1\n\nMIT",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP server for Gemini AI image processing - \u57fa\u4e8e Gemini 2.5 Flash \u7684\u56fe\u7247\u5904\u7406 MCP \u670d\u52a1",
"version": "0.2.7",
"project_urls": {
"Documentation": "https://github.com/yourusername/gemini-mcp#readme",
"Homepage": "https://github.com/yourusername/gemini-mcp",
"Issues": "https://github.com/yourusername/gemini-mcp/issues",
"Repository": "https://github.com/yourusername/gemini-mcp"
},
"split_keywords": [
"ai",
" claude",
" gemini",
" image-processing",
" llm",
" mcp"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "1fdd19fbb9b37a4b3ec0927300698ae8d52a884ad273ed8bc31cf2218f8fd4c5",
"md5": "64b642c904f762051ffe05eb30124b80",
"sha256": "77a5cc80f1d1529b36d09552e44dc4624c351ba2794e021470316b3d5504e5f9"
},
"downloads": -1,
"filename": "gemini_mcp-0.2.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "64b642c904f762051ffe05eb30124b80",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 13709,
"upload_time": "2025-09-04T04:20:21",
"upload_time_iso_8601": "2025-09-04T04:20:21.982940Z",
"url": "https://files.pythonhosted.org/packages/1f/dd/19fbb9b37a4b3ec0927300698ae8d52a884ad273ed8bc31cf2218f8fd4c5/gemini_mcp-0.2.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "eac3fe50e2e1b5e0fecf5a8aa127e3c5e69ca16f6ff8a498acad51e44e6b9875",
"md5": "cdb12570aa806e7e42b0c173c9f69cb7",
"sha256": "81dcaec954e3efaf953fca359c39f60503ab74129a85539ebc641863fb84f2d8"
},
"downloads": -1,
"filename": "gemini_mcp-0.2.7.tar.gz",
"has_sig": false,
"md5_digest": "cdb12570aa806e7e42b0c173c9f69cb7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 16039,
"upload_time": "2025-09-04T04:20:23",
"upload_time_iso_8601": "2025-09-04T04:20:23.263766Z",
"url": "https://files.pythonhosted.org/packages/ea/c3/fe50e2e1b5e0fecf5a8aa127e3c5e69ca16f6ff8a498acad51e44e6b9875/gemini_mcp-0.2.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-04 04:20:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yourusername",
"github_project": "gemini-mcp#readme",
"github_not_found": true,
"lcname": "gemini-mcp"
}
