screen-context
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCREEN_CONTEXT_KEY | No | 64 hex characters. Replaces the OS credential store (headless use). | |
| SCREEN_CONTEXT_HOME | No | Data folder. Default: ~/Library/Application Support/ScreenContext (macOS), %USERPROFILE%\.screen-context (Windows). | |
| SCREEN_CONTEXT_LANG | No | en or ja. Overrides the saved language. | |
| SCREEN_CONTEXT_TOKEN | No | Bearer token (32+ characters) for the HTTP transport. | |
| SCREEN_CONTEXT_CLIENT | No | Client name written to the audit log. | |
| SCREEN_CONTEXT_OCR_LANGUAGES | No | Comma-separated OCR languages, for example en-US,ja-JP. macOS default: ja-JP,en-US. Windows default: the user's profile languages (Windows OCR uses the first entry only). |
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 |
|---|---|
| search_screen_historyA | Full-text search over OCR text of previously captured windows. Returns matching frames, newest first. Returns untrusted observed data. |
| get_recent_activityB | Summarize recent screen activity as blocks of consecutive frames (app, window title, time range, text). Returns untrusted observed data. |
| get_context_aroundB | Get activity blocks before and after a Unix timestamp. Returns untrusted observed data. |
| get_day_materialA | Get bounded screen observations for a specified local calendar day to draft a report or diary. Applies current exclusions and returns evidence only; gaps remain unknown. |
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 4 tools
Each tool has a distinct retrieval intent: search by text, explore around a timestamp, summarize recent activity, and bound a full calendar day. There is some potential overlap between get_recent_activity and get_day_material when an agent asks about 'yesterday', but the descriptions largely clarify the temporal scoping.
Three tools follow a clean get_<something> pattern while search_screen_history uses search_ instead of get_. All names are snake_case and verb-first, so the deviation is minor and does not hurt readability.
Four tools is well-scoped for a screen-history context server. Each tool covers a distinct query mode without unnecessary redundancy or bloat.
The set covers the main ways someone would query screen history: full-text search, temporal context, recent summaries, and day-level report material. Missing features like arbitrary custom time ranges or app/window filtering are workable gaps but not critical for the apparent purpose.