Screen Capture
ClaudeMCPServer provides screen capture capabilities for AI assistants through the Model Context Protocol. This Python-based implementation uses PyAutoGUI to take screenshots, automatically compresses images to WebP format under 500KB through dynamic quality adjustment and resizing, and exposes both a resource endpoint for retrieving current screen content and a tool for capturing screens with optional custom save paths. The server can be configured through environment variables and includes robust error handling and logging, making it ideal for workflows where AI assistants need to analyze or reference what's currently on the user's screen.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/syedazharmbnr1/claudemcpserver
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Screen Capture from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.