Skip to main content
Glama
jiarong0423

Shared Room MCP

by jiarong0423
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHost to bind the server to.0.0.0.0
PORTNoPort to run the server on.3000
GEMINI_KEYNoAlternative alias for a Gemini API key (optional).
CORS_ORIGINNoAllowed origin for Socket.IO. Leave empty for same-origin deployment.
GEMINI_MODELNoGemini model to use for optional repair.gemini-2.5-flash
MAX_IMAGE_MBNoMaximum uploaded image size in MB.8
OPENAI_MODELNoOpenAI model to use for optional repair.gpt-5.4-mini
GEMINI_API_KEYNoAPI key for Google Gemini (optional, used only for repair).
GOOGLE_API_KEYNoAlias for a Google API key (optional).
OPENAI_API_KEYNoAPI key for OpenAI (optional, used only for repair).
ROOM_TTL_HOURSNoRoom lifetime in hours.12
LOCAL_OCR_FIRSTNoWhether to attempt local OCR before external providers.true
ROOM_STORE_PATHNoPath to the JSON room store. Use /data/rooms.json with a mounted volume for restart-safe demo.data/rooms.json
ROOM_PERSISTENCENoPersistence mode. Use 'json' for the default JSON file store.json
AI_PROVIDER_ORDERNoComma-separated list of AI providers to try for optional repair.gemini,openai
GEMINI_TIMEOUT_MSNoTimeout for Gemini requests in milliseconds.25000
OPENAI_TIMEOUT_MSNoTimeout for OpenAI requests in milliseconds.35000
API_RATE_LIMIT_MAXNoMaximum number of API requests per rate limit window.180
LOCAL_OCR_MAX_CHARSNoMaximum number of characters for local OCR input.12000
LOCAL_OCR_MIN_ITEMSNoMinimum number of items required for local OCR to be used.3
OPENAI_IMAGE_DETAILNoImage detail level for OpenAI vision requests.high
RATE_LIMIT_WINDOW_MSNoRate limit window in milliseconds.60000
GEMINI_RETRY_ATTEMPTSNoNumber of retry attempts for Gemini calls.2
GOOGLE_GEMINI_API_KEYNoAlias for a Google Gemini API key (optional).
GEMINI_MODEL_FALLBACKSNoComma-separated fallback Gemini models.gemini-2.5-flash-lite,gemini-flash-latest
OPENAI_MODEL_FALLBACKSNoComma-separated fallback OpenAI models.
ROOM_PERSIST_JITTER_MSNoMaximum jitter in milliseconds before saving.120
OPENAI_MAX_OUTPUT_TOKENSNoMaximum number of output tokens for OpenAI responses.16000
ROOM_PERSIST_DEBOUNCE_MSNoDebounce window in milliseconds for saving room changes.35
MENU_PARSE_RATE_LIMIT_MAXNoMaximum number of menu parse requests per rate limit window.30
ROOM_CREATE_RATE_LIMIT_MAXNoMaximum number of room creations per rate limit window.20
TRUST_LAYER_SPREADSHEET_IDNoOptional Google Sheets ID for whitelist/audit logs. Leave unset to disable.
GOOGLE_GENERATIVE_AI_API_KEYNoAlias for a Google Generative AI API key (optional).

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/jiarong0423/shared-room-mcp'

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