DSH Sticker MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QQ_BRIDGE_URL | No | The URL of the running qq-bridge server. Defaults to http://127.0.0.1:3100; only HTTP loopback addresses are allowed. | http://127.0.0.1:3100 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qq_list_stickersB | 检索当前会话可用的表情库。按标签、备注、情绪和用法查找;标签不能代替视觉确认。 |
| qq_get_sticker_imageB | 将表情图片返回给视觉模型。GIF 由兼容桥接抽帧预览;读取成功才能判断图片内容。 |
| qq_send_stickerB | 发送一张表情。可只发图,或传 caption 将文字与图片放在同一条消息;不要另发重复文字。caption 需要支持该功能的桥接版本。 |
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 3 tools
The three tools map cleanly onto distinct steps of a single workflow: search the library, fetch the image for visual inspection, send a sticker. Descriptions explicitly disambiguate related concerns (e.g. tags cannot replace visual confirmation; caption replaces separate text).
All three follow the same qq_verb_noun pattern (qq_list_stickers, qq_get_sticker_image, qq_send_sticker) with a shared namespace prefix and snake_case throughout.
Three tools are minimal but each earns its place in a narrow sticker domain. It is on the low end, though no obvious operation is missing from the discover-view-send loop.
The read-and-send lifecycle is fully covered with no dead ends. Minor gaps exist around sticker management (adding stickers, editing tags/notes) and richer metadata retrieval, but typical agent workflows are supported.