Screen View MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | Yes | Your Anthropic API key for Claude Vision API |
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 |
|---|---|
| helloWorldD | – |
| captureAndAnalyzeScreenD | – |
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 2 tools
The two tools have no descriptions, and their names suggest completely different purposes: one is a generic 'helloWorld' placeholder, while the other is a combined screen capture/analysis tool. This makes it impossible for an agent to distinguish their roles or select appropriately.
Tool names follow no consistent pattern: 'captureAndAnalyzeScreen' uses camelCase with multiple verbs, while 'helloWorld' is a simple non-descriptive name. No common verb or noun style unifies them.
With only two tools, the server is too sparse for its implied domain of screen viewing/analysis. One tool is a trivial placeholder, leaving essentially one functional tool, which is insufficient for meaningful interaction.
The server lacks essential operations for screen viewing (e.g., capture, analyze, list screens). The only relevant tool combines capture and analysis, missing other lifecycle steps, and the presence of a placeholder tool indicates severe incompleteness.