LocalLLM-MCP
by amit11-ibm
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging verbosity: DEBUG, INFO, WARNING, ERROR | INFO |
| MAX_RETRIES | No | Retry attempts on connection errors and 5xx responses | 3 |
| QWEN_ENDPOINT | No | Override endpoint for the qwen model. Format: http://host:port | |
| GEMMA_ENDPOINT | No | Override endpoint for the gemma model. Format: http://host:port | |
| LLAMA_ENDPOINT | No | Override endpoint for the llama model. Format: http://host:port | |
| GRANITE_ENDPOINT | No | Override endpoint for the granite model. Format: http://host:port | |
| NEMOTRON_ENDPOINT | No | Override endpoint for the nemotron model. Format: http://host:port | |
| REQUEST_TIMEOUT_SECONDS | No | Seconds before a request is abandoned | 120 |
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