Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GHOST_SHELLNoSet to 'off' to disable the ghost_shell verb entirely.
GHOST_CDP_ROUTENoSet to 'off' to disable Chrome DevTools Protocol routing for browser tools.
GHOST_SHELL_WARMNoSet to 'off' to disable the pre-spawned spare PowerShell process used to speed up ghost_shell commands.
GHOST_YOLO_MODELNoOptional path to an OmniParser ONNX model for the CV detection tier.
GHOST_FOCUS_POLICYNoThe process-wide focus policy. Defaults to 'background'. Set to 'foreground' for targets that require real input.
GHOST_VISION_MODELNoModel name for the vision endpoint.
GHOST_VISION_API_KEYNoAPI key for the vision endpoint. Not needed for keyless local servers.
GHOST_VISION_BASE_URLNoBase URL for an OpenAI-compatible or Anthropic vision endpoint. Required for the optional built-in vision tier.

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/NORTHTEKDevs/ghost'

If you have feedback or need assistance with the MCP directory API, please join our Discord server