aiPicMatting
图片处理-抠图
LABSCO SUMMARY
An agent can put a file in your bucket and then work on it there.
What it takes off you is the round trip: the file goes up once, and the cutout, the upscale, the watermark, the PDF conversion and the similarity search all run against the object in place rather than on your machine.
What it is
Tencent's own MCP server for Cloud Object Storage. It reads and writes one bucket, and exposes the data-processing services that run against objects already in it.
What you get
- Uploads in whatever form you have the file: a local path, a string, base64, a buffer, or a URL the server fetches itself
- A bucket listing by prefix, a direct download, or a signed link to one object
- Image work in place: metadata, quality assessment, upscaling, subject cutout, QR-code reading and a text watermark
- Dataset search for images similar to one you supply, or matching a text description
- Asynchronous jobs — a smart video cover and document-to-PDF conversion — each with a second call that collects the result by job id
- A call that reads back the region, bucket and dataset the server was started with
Requirements
npx on your PATH, plus a region, a bucket, a secret id and key, and a dataset name. All five are passed on the launch line and the server holds them for every call, so one running server serves one bucket.
Setup effort
One command — npx cos-mcp --Region=<YOUR_REGION> --Bucket=<YOUR_BUCKET> --SecretId=<YOUR_SECRET_ID> --SecretKey=<YOUR_SECRET_KEY> --DatasetName=<YOUR_DATASET_NAME>
USE CASES
01
Getting a file into the bucket from wherever it is
The upload takes whatever form you have it in — a path on disk, a string, base64, a buffer, or a URL the server fetches itself — and puts it under the directory you name.
02
Sharing one file without opening the bucket
Find the object by prefix, then hand out a signed link to that one file rather than making the bucket readable. The object can also be pulled down directly when the agent needs the bytes.
03
Getting an image ready to publish
Check what the file actually is and how good it is, scale it up if it is too small, and stamp a text watermark on it — all against the object in the bucket, with nothing downloaded.
04
Cutting a subject out of a photo
Give the object and the size you want back and the cutout runs in the bucket, so a product shot becomes a transparent asset without a round trip through an editor.
05
Finding an image you cannot name
Search the dataset by description when you remember what was in the picture, or by example when you have a similar one, instead of guessing at file names.
06
Turning a document into a PDF
Conversion is a job rather than an answer: start it against the object, keep the job id, and collect the result when it is done.
21 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
aiQrcode
图片处理-二维码识别-识别存储桶内二维码图片内容
aiSuperResolution
图片处理-超分辨率
assessQuality
图片处理-图片质量评估
createDocToPdfJob
创建文档转 pdf 处理任务
createMediaSmartCoverJob
创建媒体智能封面任务
describeDocProcessJob
根据 jobid 查询指定的文档转码任务结果
describeMediaJob
根据 jobid 查询指定的媒体智能封面任务结果
getBucket
查询存储桶内的文件列表
getCosConfig
获取COS配置, 腾讯云配置
getObject
下载存储桶内的文件
getObjectUrl
获取存储桶内的文件的带签名的下载链接
imageInfo
图片处理-获取图片信息
imageSearchPic
根据输入的图片，从数据集中检索出与输入的图片内容相似的图片
imageSearchText
根据输入的文本内容，从数据集中检索出与输入的文本内容相符的图片
putBase64
上传base64编码内容到存储桶
putBuffer
上传buffer内容到存储桶
putObject
上传本地文件到存储桶
putObjectSourceUrl
通过 url下载文件并将文件上传到存储桶
putString
上传字符串内容到存储桶
waterMarkFont
生成带文字水印的图片
BEFORE YOU INSTALL
What to know first
Tools you get
21 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 21 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"cos-mcp": {
"command": "npx",
"args": [
"cos-mcp",
"--Region=<YOUR_REGION>",
"--Bucket=<YOUR_BUCKET>",
"--SecretId=<YOUR_SECRET_ID>",
"--SecretKey=<YOUR_SECRET_KEY>",
"--DatasetName=<YOUR_DATASET_NAME>"
]
}
}
}npx
TERMINAL
npx cos-mcp --Region=<YOUR_REGION> --Bucket=<YOUR_BUCKET> --SecretId=<YOUR_SECRET_ID> --SecretKey=<YOUR_SECRET_KEY> --DatasetName=<YOUR_DATASET_NAME>
