liyakat-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the server. Automatically set if not provided. | |
| NVIDIA_API_KEY | No | API key from https://build.nvidia.com. Used for both embeddings and chat. | |
| ALLOWED_ORIGINS | No | CORS origins list. | * |
| NVIDIA_CHAT_MODEL | No | The NVIDIA chat model to use. | meta/llama-3.3-70b-instruct |
| EMBEDDING_PROVIDER | No | If 'local', uses a local embedding server; otherwise hosted (OpenRouter/OrcaRouter). | |
| OPENROUTER_API_KEY | No | Alternative to NVIDIA_API_KEY. Use OpenRouter instead of NVIDIA. | |
| ORCAROUTER_API_KEY | No | Alternative to NVIDIA_API_KEY. Use OrcaRouter instead of NVIDIA. | |
| LOCAL_EMBEDDING_MODEL | No | Model name for the local embedding server (e.g., intfloat/multilingual-e5-large). | |
| EMBEDDING_PROMPT_STYLE | No | Prompt style expected by the embedding model: 'gemini', 'e5', or 'raw'. | gemini |
| NVIDIA_EMBEDDING_MODEL | No | The NVIDIA embedding model to use. | nvidia/nv-embed-v1 |
| LOCAL_EMBEDDING_BASE_URL | No | Base URL of the local embedding server, OpenAI-compatible (e.g., http://localhost:8080/v1). | |
| LOCAL_EMBEDDING_DIMENSION | No | Output dimension of the local embedding model (e.g., 1024). | |
| OPENROUTER_EMBEDDING_MODEL | No | OpenRouter embedding model ID (e.g., google/gemini-embedding-001). | |
| ORCAROUTER_EMBEDDING_MODEL | No | OrcaRouter embedding model ID (e.g., google/gemini-embedding-001). | |
| OPENROUTER_EMBEDDING_DIMENSION | No | Output dimension of the OpenRouter embedding model (e.g., 3072). | |
| ORCAROUTER_EMBEDDING_DIMENSION | No | Output dimension of the OrcaRouter embedding model (e.g., 3072). |
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