Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ZJU_MCP_HOSTNoHTTP listen address.127.0.0.1
ZJU_MCP_PORTNoHTTP listen port.8000
ZJU_MCP_RETRIESNoNumber of retries for transient network failures.1
PYTHONIOENCODINGNoPython standard I/O encoding; the example configuration sets this to utf-8.
ZJU_MCP_CACHE_PATHNoSQLite file location for cached snapshots. On Windows, the default is %LOCALAPPDATA%\zju-teacher-mcp\cache.sqlite3.%LOCALAPPDATA%\zju-teacher-mcp\cache.sqlite3
ZJU_MCP_CONCURRENCYNoMaximum number of concurrent upstream requests.2
ZJU_MCP_CALL_TIMEOUTNoTotal time budget for a single tool call, in seconds.45
ZJU_MCP_REQUEST_TIMEOUTNoTimeout for a single upstream request, in seconds.15
ZJU_MCP_REQUEST_INTERVALNoMinimum interval between requests to the same origin, in seconds.0.5
ZJU_MCP_MAX_RESPONSE_BYTESNoMaximum decompressed response size in bytes.5000000
ZJU_MCP_SNAPSHOT_TTL_HOURSNoValidity time for continuation snapshots, in hours.24
ZJU_MCP_CACHE_RETENTION_HOURSNoRetention time for normal snapshots, in hours.168

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