llm-gateway
by karolnowacki
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Bind address (HTTP transports). | 127.0.0.1 |
| MCP_PORT | No | Bind port (HTTP transports). | 1235 |
| OPENCODE_URL | No | opencode serve endpoint for opencode and browser. | http://127.0.0.1:4096 |
| MCP_TRANSPORT | No | Transport: streamable-http, sse, or stdio. | streamable-http |
| OPENAI_API_KEY | No | Backend API key. | lmstudio |
| OPENAI_BASE_URL | No | OpenAI-compatible backend for compression. | http://127.0.0.1:1234/v1 |
| COMPRESSOR_MODEL | No | Model to use; empty lets the backend use its loaded model. | |
| CODEX_APP_SERVER_SOCKET | No | Codex app-server unix socket. | $XDG_RUNTIME_DIR/codex-app-server/app-server.sock |
| LLM_GATEWAY_ALLOW_REMOTE | No | Set to 1 to allow a non-loopback MCP_HOST. | |
| LLM_GATEWAY_ALLOWED_HOSTS | No | Extra allowed Host values, comma-separated (e.g. 192.168.1.5:1235). | |
| CODEX_APP_SERVER_TRANSPORT | No | Codex socket protocol: websocket or jsonl. | websocket |
| COMPRESSOR_MAX_INPUT_CHARS | No | Input size cap before truncation. | 100000 |
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
ActivitySlowing
ResponsivenessNo issues