Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LANHU_AI_MODELNoModel name sent to the compatible AI service.
LANHU_FLOW_DIRNoDirectory for page-flow JSON files..lanhu/flows
LANHU_HEADLESSNoWhether Chromium runs headless for MCP calls.true
LANHU_AI_API_KEYNoOptional local environment variable for the AI API key. Takes precedence over the key file.
LANHU_TIMEOUT_MSNoTimeout for page and asset requests in milliseconds.30000
LANHU_AI_BASE_URLNoLocal OpenAI-compatible service base URL, for example `http://127.0.0.1:1234/v1`.
LANHU_AI_PROVIDERNoProvider identifier shown in the AI settings UI.custom
FIGMA_ACCESS_TOKENNoOptional Figma access token environment variable. Takes precedence over the token file.
LANHU_DOWNLOAD_DIRNoDirectory for downloaded assets.downloads
LANHU_PROJECT_ROOTNoBase path for resolving `.env`, `.auth`, and download directories. Defaults to the current directory.
FIGMA_STORAGE_STATENoFigma browser login state file. Defaults to using LANHU_STORAGE_STATE.
LANHU_AI_TIMEOUT_MSNoTimeout for AI optimization requests in milliseconds.30000
LANHU_STORAGE_STATENoPlaywright login state file for Lanhu..auth/storage-state.json
LANHU_AI_API_KEY_FILENoLocal AI API key file. May be omitted for local services without authentication..auth/ai-api-key
LANHU_AI_SETTINGS_FILENoAI settings file for the endpoint and model saved from the UI..auth/ai-settings.json
MOCKPLUS_STORAGE_STATENoMockplus browser login state file. Defaults to using LANHU_STORAGE_STATE.
FIGMA_ACCESS_TOKEN_FILENoFigma official API token file. When present, enables Figma API mode..auth/figma-api-token
LANHU_MAX_DOWNLOAD_BYTESNoMaximum size in bytes for a single downloaded asset (50 MiB by default).52428800
LANHU_DEFAULT_VIEWPORT_WIDTHNoDefault browser viewport width.1440
LANHU_BROWSER_EXECUTABLE_PATHNoOptional path to a Chrome/Chromium executable. Defaults to the Playwright bundled browser.
LANHU_DEFAULT_VIEWPORT_HEIGHTNoDefault browser viewport height.900

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

Maintenance

ActivityMaintained
ResponsivenessNo issues