Skip to main content
Glama
Jostophe-021

mcp-cross-model-delegation

by Jostophe-021

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort for the MCP server. Safe range 1–65535. Defaults to 8000.8000
MCP_HOSTNoHost to bind the MCP server to. Only 127.0.0.1 or localhost allowed. Defaults to 127.0.0.1.127.0.0.1
GEMINI_MODELNoGemini model ID; validate availability yourself. Defaults to gemini-3.5-flash-lite.gemini-3.5-flash-lite
GEMINI_API_KEYYesRequired for real calls. Keep outside source and image.
MAX_TASK_CHARSNoMaximum task length in characters. Safe range 1–12000. Defaults to 12000.12000
MAX_CONTEXT_CHARSNoMaximum context length in characters. Safe range 1–200000. Defaults to 100000.100000
MAX_OUTPUT_TOKENSNoMaximum output tokens. Safe range 256–8192. Defaults to 4096.4096
MODEL_TIMEOUT_SECONDSNoRequest timeout in seconds. Safe range 1–120. Defaults to 60.60

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