Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_MODELNoOllama model name, default gemma4:e4b-it-q4_K_M.
AGENT_EYE_MODELNoContent-budget model for browser_get_content (deep-seek, llama2, default).
OLLAMA_BASE_URLNoBase URL for Ollama, default http://localhost:11434.
AGENT_EYE_HEADLESSNoRun browser in headless mode (true/false).
AGENT_EYE_MAX_CHARSNoMaximum characters for content extraction, default 50000.
AGENT_EYE_PROFILE_ROOTNoRoot directory for browser profiles, default ~/.agent-eye/profiles.
AGENT_EYE_NAV_TIMEOUT_MSNoNavigation timeout in milliseconds, default 30000.
AGENT_EYE_SKILL_STALE_FOCUSED_CHARSNoRefresh skill if cached focused content is too small, default 400.
AGENT_EYE_SKILL_STALE_SELECTOR_MATCHESNoRefresh skill if cached selectors barely match DOM, default 1.
AGENT_EYE_SKILL_STALE_FAILURE_THRESHOLDNoRefresh skill after repeated selector failures, default 2.

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/henry0hai/agent-eyes'

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