llm-prompt-optimizer
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LPO_MCP_HOST | No | Host address for MCP server (HTTP/WebSocket). Default 127.0.0.1. | 127.0.0.1 |
| LPO_MCP_PORT | No | Port for MCP server. Default 8765. | 8765 |
| LPO_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR). Default INFO. | INFO |
| LPO_TOKEN_BUDGET | No | Maximum token budget for optimized prompt. Default 8000. | 8000 |
| LPO_MCP_TRANSPORT | No | Transport protocol for MCP server: stdio, http, websocket. Default stdio. | stdio |
| LPO_STRICT_INTENT | No | Enable strict intent mode (true/false). Default depends on configuration. | false |
| LPO_GRAPH_PROVIDER | No | Optional graph provider endpoint. Default empty (uses fallback). | |
| LPO_SEMANTIC_THRESHOLD | No | Semantic similarity threshold for validation (e.g., 0.90). Default 0.90. | 0.90 |
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
ActivityInactive
ResponsivenessNo issues