mcp-cross-model-delegation
by Jostophe-021
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the MCP server. Safe range 1–65535. Defaults to 8000. | 8000 |
| MCP_HOST | No | Host 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_MODEL | No | Gemini model ID; validate availability yourself. Defaults to gemini-3.5-flash-lite. | gemini-3.5-flash-lite |
| GEMINI_API_KEY | Yes | Required for real calls. Keep outside source and image. | |
| MAX_TASK_CHARS | No | Maximum task length in characters. Safe range 1–12000. Defaults to 12000. | 12000 |
| MAX_CONTEXT_CHARS | No | Maximum context length in characters. Safe range 1–200000. Defaults to 100000. | 100000 |
| MAX_OUTPUT_TOKENS | No | Maximum output tokens. Safe range 256–8192. Defaults to 4096. | 4096 |
| MODEL_TIMEOUT_SECONDS | No | Request 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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessUnresponsive