Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | HTTP mode: host to bind to | 0.0.0.0 |
| MCP_PORT | No | HTTP mode: port to listen on | 8000 |
| LLM_MODEL | No | Azure OpenAI model to use (e.g., gpt-4o-global, gpt-4o-mini-global) | gpt-4o-global |
| GEMINI_MODEL | No | Google Gemini model to use (e.g., gemini-2.0-flash-exp, gemini-1.5-pro) | gemini-2.0-flash-exp |
| LLM_PROVIDER | No | LLM provider to use (openai or gemini) | openai |
| MCP_TRANSPORT | No | MCP transport mode (http for network access or stdio for local) | http |
| GOOGLE_API_KEY | No | Your Google API key from aistudio.google.com | |
| LLM_ENVIRONMENT | No | Azure OpenAI environment (nonprod or prod) | nonprod |
| AZURE_OPENAI_KEY | No | Your Azure OpenAI API key from genai.web.bms.com | |
| EMBEDDING_PROVIDER | No | Embedding provider to use (local for BGE-M3, onnx for lightweight local, openai for Azure OpenAI, or gemini for Google Gemini) | local |
| ONNX_EMBEDDING_MODEL | No | ONNX embedding model to use (e.g., all-MiniLM-L6-v2, all-mpnet-base-v2) | all-MiniLM-L6-v2 |
| GEMINI_EMBEDDING_MODEL | No | Google Gemini embedding model to use | text-embedding-004 |
| AZURE_OPENAI_API_VERSION | No | Azure OpenAI API version | 2024-02-01 |
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 | |