MCP Gateway
by danielsmag
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub personal access token used by the GitHub MCP server (if enabled). | |
| FRONTEND_PORT | No | Port for the React console service. | |
| SAFE_DB_SCHEMA | No | Database schema used for gateway sessions. | |
| GATEWAY_LOG_LEVEL | No | Log level (e.g., DEBUG). | |
| GATEWAY_LLM__BASE_URL | No | Base URL for the OpenAI-compatible local model API (e.g., http://localhost:11434/v1). | |
| GATEWAY_GUARD__ENABLED | No | Enable the local LLM safety guard (true/false). | |
| GATEWAY_LLM__AGENT_MODEL | No | Model used by the red-team agent. | |
| GATEWAY_SESSION__IDLE_TTL_SECONDS | No | Idle timeout for MCP sessions in seconds. Default 24 hours (0 disables). |
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 | |