Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoListening address127.0.0.1
PORTNoListening port3000
MCP_NAMENoService identifier reported in initializemcp-cogview
MCP_PATHNoStreamable HTTP endpoint/mcp
LOG_LEVELNoLog level: debug/info/warn/errorinfo
GLM_API_KEYNoAlias for ZHIPU_API_KEY
MCP_VERSIONNoService version0.1.0
COGVIEW_MOCKNoEnable mock mode; automatically true if no API key set
COGVIEW_SIZENoDefault size1024x1024
COGVIEW_MODELNoDefault modelcogview-3-plus
MCP_LIVE_PATHNoLiveness probe path/live
MCP_STATELESSNoStateless mode (each request gets an independent server)false
ZHIPU_API_KEYNoZhipu API Key (also accepts GLM_API_KEY / COGVIEW_API_KEY)
COGVIEW_API_KEYNoAlias for ZHIPU_API_KEY
COGVIEW_ENDPOINTNoText-to-image API endpointhttps://open.bigmodel.cn/api/paas/v4/images/generations
MCP_ALLOWED_ORIGINSNoComma-separated origin whitelist; enables DNS rebinding protection if set
MCP_SESSION_IDLE_MSNoSession idle reclamation threshold, 0 means no reclamation600000
COGVIEW_POLL_TIMEOUT_MSNoAsync task maximum wait time120000
COGVIEW_RESPONSE_FORMATNoDefault response formaturl
COGVIEW_POLL_INTERVAL_MSNoAsync task polling interval2000
COGVIEW_REQUEST_TIMEOUT_MSNoSingle HTTP request timeout60000

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/Superlittlemy/image_mcp'

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