| Name | qihoo-fgclip-mcp JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | None |
| Summary | MCP Server for 360 Research embedding services |
| upload_time | 2025-08-28 08:40:25 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
360
ai
embedding
mcp
research
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# qihoo-fgclip-mcp
MCP (Model Context Protocol) Server for 360 Research embedding services.
## 功能特性
这个MCP服务器提供了以下工具：
- **text_embedding**: 为文本生成嵌入向量
- **image_embedding**: 为图像生成嵌入向量
- **embedding**: 通用的文本或图像嵌入向量生成工具
## 安装
```bash
# 使用uv安装依赖
uv sync
```
## 配置
设置环境变量：
```bash
export MCP_API_KEY="your_360_research_api_key"
export MCP_API_BASE_URL="https://api.research.360.cn/models/interface"
```
## 使用方法
### 作为MCP服务器运行
```bash
# 使用stdio传输（推荐用于uvx）
python main.py --transport stdio
# 使用HTTP传输
python main.py --transport http --host 0.0.0.0 --port 8000
```
### 作为可执行脚本运行
```bash
# 安装后可以直接运行
qihoo-fgclip-mcp --transport stdio
```
## 工具说明
### text_embedding
为文本生成嵌入向量。
参数：
- `texts`: 要嵌入的文本字符串列表
- `model`: 使用的模型（默认: "fg-clip"）
- `embedding_types`: 返回的嵌入类型（默认: ["float"]）
- `truncate`: 截断策略（"start", "end", "none"，默认: "start"）
### image_embedding
为图像生成嵌入向量。
参数：
- `images`: 图像URL或base64编码图像的列表
- `model`: 使用的模型（默认: "fg-clip"）
- `embedding_types`: 返回的嵌入类型（默认: ["float"]）
### embedding
通用的文本或图像嵌入向量生成工具。
参数：
- `inputs`: 文本字符串或图像URL/base64的列表
- `input_type`: 输入类型（"text" 或 "image"）
- `model`: 使用的模型（默认: "fg-clip"）
- `embedding_types`: 返回的嵌入类型（默认: ["float"]）
- `truncate`: 截断策略（仅用于文本，默认: "start"）
## 开发
```bash
# 安装开发依赖
uv sync --dev
# 运行测试
python -m pytest
```
## 许可证
MIT License
Raw data
{
"_id": null,
"home_page": null,
"name": "qihoo-fgclip-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "360, ai, embedding, mcp, research",
"author": null,
"author_email": "Your Name <your.email@example.com>",
"download_url": "https://files.pythonhosted.org/packages/6c/48/e7510fe7d4267ec11bda51e4a2c8227de5bc182fdb85ea1d8e424b205fd3/qihoo_fgclip_mcp-0.1.2.tar.gz",
"platform": null,
"description": "# qihoo-fgclip-mcp\n\nMCP (Model Context Protocol) Server for 360 Research embedding services.\n\n## \u529f\u80fd\u7279\u6027\n\n\u8fd9\u4e2aMCP\u670d\u52a1\u5668\u63d0\u4f9b\u4e86\u4ee5\u4e0b\u5de5\u5177\uff1a\n\n- **text_embedding**: \u4e3a\u6587\u672c\u751f\u6210\u5d4c\u5165\u5411\u91cf\n- **image_embedding**: \u4e3a\u56fe\u50cf\u751f\u6210\u5d4c\u5165\u5411\u91cf \n- **embedding**: \u901a\u7528\u7684\u6587\u672c\u6216\u56fe\u50cf\u5d4c\u5165\u5411\u91cf\u751f\u6210\u5de5\u5177\n\n## \u5b89\u88c5\n\n```bash\n# \u4f7f\u7528uv\u5b89\u88c5\u4f9d\u8d56\nuv sync\n```\n\n## \u914d\u7f6e\n\n\u8bbe\u7f6e\u73af\u5883\u53d8\u91cf\uff1a\n\n```bash\nexport MCP_API_KEY=\"your_360_research_api_key\"\nexport MCP_API_BASE_URL=\"https://api.research.360.cn/models/interface\"\n```\n\n## \u4f7f\u7528\u65b9\u6cd5\n\n### \u4f5c\u4e3aMCP\u670d\u52a1\u5668\u8fd0\u884c\n\n```bash\n# \u4f7f\u7528stdio\u4f20\u8f93\uff08\u63a8\u8350\u7528\u4e8euvx\uff09\npython main.py --transport stdio\n\n# \u4f7f\u7528HTTP\u4f20\u8f93\npython main.py --transport http --host 0.0.0.0 --port 8000\n```\n\n### \u4f5c\u4e3a\u53ef\u6267\u884c\u811a\u672c\u8fd0\u884c\n\n```bash\n# \u5b89\u88c5\u540e\u53ef\u4ee5\u76f4\u63a5\u8fd0\u884c\nqihoo-fgclip-mcp --transport stdio\n```\n\n## \u5de5\u5177\u8bf4\u660e\n\n### text_embedding\n\n\u4e3a\u6587\u672c\u751f\u6210\u5d4c\u5165\u5411\u91cf\u3002\n\n\u53c2\u6570\uff1a\n- `texts`: \u8981\u5d4c\u5165\u7684\u6587\u672c\u5b57\u7b26\u4e32\u5217\u8868\n- `model`: \u4f7f\u7528\u7684\u6a21\u578b\uff08\u9ed8\u8ba4: \"fg-clip\"\uff09\n- `embedding_types`: \u8fd4\u56de\u7684\u5d4c\u5165\u7c7b\u578b\uff08\u9ed8\u8ba4: [\"float\"]\uff09\n- `truncate`: \u622a\u65ad\u7b56\u7565\uff08\"start\", \"end\", \"none\"\uff0c\u9ed8\u8ba4: \"start\"\uff09\n\n### image_embedding\n\n\u4e3a\u56fe\u50cf\u751f\u6210\u5d4c\u5165\u5411\u91cf\u3002\n\n\u53c2\u6570\uff1a\n- `images`: \u56fe\u50cfURL\u6216base64\u7f16\u7801\u56fe\u50cf\u7684\u5217\u8868\n- `model`: \u4f7f\u7528\u7684\u6a21\u578b\uff08\u9ed8\u8ba4: \"fg-clip\"\uff09\n- `embedding_types`: \u8fd4\u56de\u7684\u5d4c\u5165\u7c7b\u578b\uff08\u9ed8\u8ba4: [\"float\"]\uff09\n\n### embedding\n\n\u901a\u7528\u7684\u6587\u672c\u6216\u56fe\u50cf\u5d4c\u5165\u5411\u91cf\u751f\u6210\u5de5\u5177\u3002\n\n\u53c2\u6570\uff1a\n- `inputs`: \u6587\u672c\u5b57\u7b26\u4e32\u6216\u56fe\u50cfURL/base64\u7684\u5217\u8868\n- `input_type`: \u8f93\u5165\u7c7b\u578b\uff08\"text\" \u6216 \"image\"\uff09\n- `model`: \u4f7f\u7528\u7684\u6a21\u578b\uff08\u9ed8\u8ba4: \"fg-clip\"\uff09\n- `embedding_types`: \u8fd4\u56de\u7684\u5d4c\u5165\u7c7b\u578b\uff08\u9ed8\u8ba4: [\"float\"]\uff09\n- `truncate`: \u622a\u65ad\u7b56\u7565\uff08\u4ec5\u7528\u4e8e\u6587\u672c\uff0c\u9ed8\u8ba4: \"start\"\uff09\n\n## \u5f00\u53d1\n\n```bash\n# \u5b89\u88c5\u5f00\u53d1\u4f9d\u8d56\nuv sync --dev\n\n# \u8fd0\u884c\u6d4b\u8bd5\npython -m pytest\n```\n\n## \u8bb8\u53ef\u8bc1\n\nMIT License\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP Server for 360 Research embedding services",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/yourusername/qihoo-fgclip-mcp",
"Issues": "https://github.com/yourusername/qihoo-fgclip-mcp/issues",
"Repository": "https://github.com/yourusername/qihoo-fgclip-mcp"
},
"split_keywords": [
"360",
" ai",
" embedding",
" mcp",
" research"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "598d80eb65852073717823fc91ec58d28b312d589f42932a0228a985dbf131da",
"md5": "d9b4d0d4b9faaf756cfde9b8ef1f39f7",
"sha256": "790d80d0c0d76709e8f3dc02481509b9e5e6bfefc16674116d265f7a5fb891be"
},
"downloads": -1,
"filename": "qihoo_fgclip_mcp-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d9b4d0d4b9faaf756cfde9b8ef1f39f7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 6895,
"upload_time": "2025-08-28T08:40:23",
"upload_time_iso_8601": "2025-08-28T08:40:23.619871Z",
"url": "https://files.pythonhosted.org/packages/59/8d/80eb65852073717823fc91ec58d28b312d589f42932a0228a985dbf131da/qihoo_fgclip_mcp-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6c48e7510fe7d4267ec11bda51e4a2c8227de5bc182fdb85ea1d8e424b205fd3",
"md5": "eb5489cb367d4a39d66560a12708a441",
"sha256": "676dc6f9f4f877bde8ecf10b88dceb3ca82bbccf542255e61e4b96d3d176d979"
},
"downloads": -1,
"filename": "qihoo_fgclip_mcp-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "eb5489cb367d4a39d66560a12708a441",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 59595,
"upload_time": "2025-08-28T08:40:25",
"upload_time_iso_8601": "2025-08-28T08:40:25.313171Z",
"url": "https://files.pythonhosted.org/packages/6c/48/e7510fe7d4267ec11bda51e4a2c8227de5bc182fdb85ea1d8e424b205fd3/qihoo_fgclip_mcp-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-28 08:40:25",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yourusername",
"github_project": "qihoo-fgclip-mcp",
"github_not_found": true,
"lcname": "qihoo-fgclip-mcp"
}
