screen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEBP_QUALITY | No | 存储帧的 WebP 压缩质量（1-100） | 75 |
| ANTHROPIC_MODEL | Yes | 调用的模型名（必填） | |
| VISION_PROVIDER | No | 目前只实现了 anthropic | anthropic |
| CAPTURE_MAX_EDGE | No | 发给视觉 API 前的长边像素上限 | 1564 |
| MAX_FRAME_BUFFER | No | 滑动窗口大小 | 20 |
| ANTHROPIC_API_KEY | Yes | API 密钥（必填）。如果设置了 ANTHROPIC_AUTH_TOKEN 且未设置此变量，将自动使用 ANTHROPIC_AUTH_TOKEN。 | |
| ANTHROPIC_BASE_URL | No | 留空走官方 API；填了就走该 URL 下的 /v1/messages | |
| PHASH_DEDUPE_LOOKBACK | No | 与最近多少帧做 phash 比较 | 3 |
| PHASH_DEDUPE_THRESHOLD | No | 汉明距阈值，低于此值视为重复帧丢弃 | 6 |
| DEFAULT_POLLING_INTERVAL | No | 轮询模式下相邻两次采集的间隔（秒） | 3.0 |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_captureA | Begin a screen-capture session. mode='fullscreen' works on every platform; mode='window' is Windows-only and requires |
| stop_captureA | End the current capture session. |
| capture_nowA | Take a single screenshot on demand. Returns frame metadata (id, size, phash, timestamp) — NOT the image bytes. Use analyze_screen to actually read the content. |
| set_pollingB | Enable or disable a low-frequency background polling loop that keeps the frame buffer fresh. Default interval is 3 seconds. |
| list_windowsA | List visible top-level windows. On non-Windows platforms returns []. |
| analyze_screenA | Send recent frames to the configured vision provider along with the user's question, and return the model's answer. lookback_frames controls how many of the most recent frames to include (default 3). |
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 6 tools
Each tool has a clear, distinct purpose: capture management, single capture, analysis, window listing, and polling control. No overlap in functionality.
All tools follow a consistent verb_noun snake_case pattern (e.g., start_capture, analyze_screen), making intent predictable.
6 tools is well-scoped for a screen capture and analysis server, covering core operations without excess or deficiency.
Covers essential lifecycle (start/stop, single capture, analysis, window listing), but lacks frame retrieval by ID and capture region configuration, which are minor gaps.