Skip to main content
Glama
Sign In
local-llm-mcp

local-llm-mcp

by Qinlupfu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Start Server

start_server

Launch llama-server for a specified model and block until the health check passes, so local chat clients can connect to a ready GGUF model.

Instructions

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"]。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model_id": "<model_id>"
    },
    "name": "start_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
ctx_lenNo
model_idYes
extra_argsNo
gpu_layersNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses that the call blocks until the health check passes, which is non-obvious and operationally important. However, it omits what happens if a server is already running, whether an existing process is replaced, timeout/failure behavior, and resource cost.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence front-loads the action and its blocking semantics, and the second sentence is dense parameter guidance with no filler. It is compact and well ordered, though the parameter notes are packed without visual separation from the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. Yet for a process-launching tool the description lacks state-conflict handling, failure modes, and coverage of ctx_len, so it is only partly sufficient for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the sentinel value for gpu_layers (None = full VRAM offload) and gives a concrete extra_args example, but says nothing about ctx_len's meaning or sensible ranges, leaving two of four parameters undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific action (启动 llama-server) plus the resource it operates on (loading a specified model) and even discloses the completion condition (blocking until health check passes). This cleanly distinguishes it from siblings like stop_server, server_status, and runtime_info.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete pre-call guidance: use the result of suggest_gpu_layers when VRAM is insufficient, and pass extra_args=["--cpu-moe"] for MoE hybrid inference. It does not state what to do if a server is already running or how this relates to server_status, so no explicit exclusions are offered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools