llama-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLAMA_MODEL_PATH | No | Path to GGUF model file | |
| LLAMA_SERVER_URL | No | URL of llama-server | http://localhost:8080 |
| LLAMA_SERVER_PATH | No | Path to llama-server binary | llama-server |
| LLAMA_SERVER_TIMEOUT | No | Request timeout in ms | 30000 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| llama_healthB | Check if llama-server is running and get status |
| llama_propsB | Get or set server properties and default generation settings |
| llama_modelsA | List available/loaded models |
| llama_slotsA | View current slot processing state |
| llama_metricsA | Get Prometheus-compatible metrics (tokens processed, latency, etc.) |
| llama_tokenizeC | Convert text to token IDs |
| llama_detokenizeB | Convert token IDs back to text |
| llama_apply_templateA | Format chat messages using model's template without inference |
| llama_completeB | Generate text completion from a prompt |
| llama_chatC | Chat completion (OpenAI-compatible format) |
| llama_embedC | Generate embeddings for text |
| llama_infillC | Code completion with prefix and suffix context (fill-in-middle) |
| llama_rerankB | Rerank documents by relevance to a query |
| llama_load_modelC | Load a model (router mode only) |
| llama_unload_modelB | Unload the current model (router mode only) |
| llama_lora_listA | List loaded LoRA adapters |
| llama_lora_setC | Set LoRA adapter scales |
| llama_startB | Start llama-server as a child process with the specified model |
| llama_stopA | Stop the running llama-server process |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Each tool targets a distinct operation or resource: chat vs. completion vs. infill vs. embed vs. rerank, plus model and server management. No ambiguous overlaps.
All tools follow the 'llama_' prefix with lowercase snake_case names, using verbs or verb_noun patterns consistently.
19 tools is slightly above the typical 3-15 range, but each tool serves a clear purpose covering model interaction, management, and server control, so it remains reasonable.
The tool set covers the full lifecycle: chat/completion/infill/embed/rerank, tokenization, model loading/management, server health and metrics, and LoRA adapter control. No obvious gaps.