Windows-MCP
by Books-QAQ
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODE | No | Set to 'remote' to run in remote mode (requires registration at windowsmcp.io). | |
| API_KEY | No | API key required for remote mode. | |
| SANDBOX_ID | No | Sandbox ID required for remote mode. | |
| PLANNER_MODEL | No | Model name used for task planning. | deepseek-chat |
| PLANNER_API_KEY | No | API key for LLM task planning (required for smart planning feature). | |
| VALIDATOR_MODEL | No | Model name used for visual validation. | deepseek-chat |
| PLANNER_BASE_URL | No | Base URL for the LLM API used by the planner. | https://api.deepseek.com/v1 |
| VALIDATOR_API_KEY | No | API key for visual validation of task results. | |
| WINDOWS_MCP_DEBUG | No | Set to '1' or 'true' to enable debug logging. | false |
| ANONYMIZED_TELEMETRY | No | Set to 'false' to disable anonymous telemetry. | true |
| WINDOWS_MCP_PROFILE_SNAPSHOT | No | Set to '1' or 'true' to enable performance timing logs for snapshots. | false |
| WINDOWS_MCP_SCREENSHOT_SCALE | No | Screenshot scaling factor (0.1–1.0). Use 0.5 for 4K screens to stay under the 1MB limit. | 1.0 |
| WINDOWS_MCP_SCREENSHOT_BACKEND | No | Screenshot backend: 'auto', 'dxcam', 'mss', or 'pillow'. | auto |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues