Tencent Cloud COS MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| port | No | Optional parameter, when connection type is 'sse', you can freely set the port | 3001 |
| Bucket | No | Your COS bucket name (e.g. mybucket-123456) | |
| Region | No | The region where your COS bucket is located (e.g. ap-beijing) | |
| SecretId | No | Your Tencent Cloud SecretId for authentication | |
| SecretKey | No | Your Tencent Cloud SecretKey for authentication | |
| cos-config | No | JSON string containing COS configuration parameters (Region, Bucket, SecretId, SecretKey, DatasetName) | |
| DatasetName | No | Optional parameter, required for data intelligent retrieval operations | |
| connectType | No | Optional parameter to specify connection type, can be 'stdio' (local) or 'sse' (remote) | stdio |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| getCosConfigC | 获取COS配置, 腾讯云配置 |
| putObjectC | 上传本地文件到存储桶 |
| putObjectSourceUrlC | 通过 url下载文件并将文件上传到存储桶 |
| getObjectUrlC | 获取存储桶内的文件的带签名的下载链接 |
| getObjectC | 下载存储桶内的文件 |
| getBucketB | 查询存储桶内的文件列表 |
| imageInfoC | 图片处理-获取图片信息 |
| assessQualityC | 图片处理-图片质量评估 |
| aiSuperResolutionC | 图片处理-超分辨率 |
| aiPicMattingD | 图片处理-抠图 |
| aiQrcodeB | 图片处理-二维码识别-识别存储桶内二维码图片内容 |
| waterMarkFontC | 生成带文字水印的图片 |
| createMediaSmartCoverJobD | 创建媒体智能封面任务 |
| describeMediaJobB | 根据 jobid 查询指定的媒体智能封面任务结果 |
| imageSearchPicC | 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 |
| imageSearchTextC | 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 |
| createDocToPdfJobC | 创建文档转 pdf 处理任务 |
| describeDocProcessJobC | 根据 jobid 查询指定的文档转码任务结果 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 18 tools
Most tools have distinct purposes, such as getBucket for listing files, putObject for uploading, and aiPicMatting for image matting. However, some overlap exists between imageSearchPic and imageSearchText, both involving image retrieval, which could cause minor confusion. Overall, the descriptions clarify boundaries well.
The naming is mixed with camelCase (e.g., aiPicMatting) and snake_case (e.g., get_object_url), lacking a uniform pattern. While verbs like 'create', 'describe', 'get', and 'put' are used consistently, the inconsistency in case styles reduces predictability. It remains readable but not fully standardized.
With 18 tools, the count is slightly high but reasonable for a cloud storage and processing server. It covers file operations, image processing, and media tasks without feeling overly bloated. The scope justifies most tools, though it borders on being heavy.
The server provides good coverage for COS operations, including CRUD-like actions (get, put) and advanced processing (image, media, document tasks). Minor gaps exist, such as no direct update or delete tools for objects, but agents can work around this using upload/overwrite or other methods. The surface is largely complete for the domain.