local-llm-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MCP_PORT | No | llama-server 端口 | 18787 |
| LLM_MCP_LOG_DIR | No | llama-server 日志目录 | <项目>/.runtime_logs |
| LLM_MCP_LLAMA_DIR | No | llama.cpp 目录 | D:\AITools\LLMTools\llama-b10930-bin-win-cuda-13.3-x64 |
| LLM_MCP_STATE_FILE | No | 运行时状态文件 | <项目>/.runtime_state.json |
| LLM_MCP_MODELS_ROOT | No | GGUF 模型根目录 | E:\AI-models\LLM |
| LLM_MCP_CHAT_TIMEOUT | No | chat 超时（秒）；35B 混合推理较慢，给足余量 | 300 |
| LLM_MCP_IDLE_TIMEOUT | No | 闲置自动卸载（秒），0=不自动卸载；应大于 chat 超时 | 600 |
| LLM_MCP_START_TIMEOUT | No | 启动健康等待上限（秒） | 180 |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pingA | 连通性测试，返回 pong。 |
| runtime_infoA | 返回模型目录与 llama-server 路径，用于确认配置就绪。 |
| list_modelsB | 扫描本地模型目录，返回所有 GGUF 主模型的元数据（含多模态投影探测）。 |
| estimate_vramC | 估算模型显存占用（权重+KV+开销），附带建议的 GPU offload 层数 （返回中的 suggested_gpu_layers 字段）。 |
| suggest_gpu_layersC | 在显存预算内建议最大的 GPU offload 层数；放不下时提示需要 CPU 混合。 |
| start_serverA | 启动 llama-server 加载指定模型，阻塞到健康检查通过。 gpu_layers=None 表示全量进显存；显存不够的模型可用 suggest_gpu_layers 的结果， MoE 大模型混合推理推荐 extra_args=["--cpu-moe"]。 |
| stop_serverA | 停止本地模型服务并释放显存。幂等：未运行时也正常返回。 |
| server_statusA | 查询本地模型服务状态（进程/健康/加载的模型/闲置计时）。 |
| chatA | 把对话发给已加载的本地模型（OpenAI 消息格式 [{"role","content"}]）。 先用 start_server 启动模型；返回 {"content", "reasoning", "model", "usage"}。 |
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 9 tools
Most tools target distinct actions: ping, runtime_info, list_models, start/stop/status, chat. The only notable overlap is between estimate_vram and suggest_gpu_layers, since estimate_vram already returns a suggested_gpu_layers field; an agent could be unsure which to call for layer suggestions. Descriptions help but this pair remains somewhat confused.
All names use snake_case, which is consistent. However, the pattern is mixed: some are verb_noun (list_models, start_server, estimate_vram), while others are noun phrases (runtime_info, server_status) or simple verbs (ping, chat). Minor deviations keep it from a perfect verb_noun pattern.
Nine tools is well-scoped for local LLM server management. The set covers lifecycle, inspection, resource estimation, and inference without obvious bloat. Each tool has a clear role, making the count appropriate.
The surface covers core workflows: start/stop server, status, model listing, VRAM estimation, GPU layer suggestion, and chat. Minor gaps exist, such as no tool to stream or cancel an in-progress chat, no model download, and no configuration update. These are workable around but leave the surface slightly incomplete.