MCP Local Llm
未认领MCP server for delegating mechanical tasks to local LLMs via Ollama. Claude does the thinking, your local model does the grunt work.
安装
claude mcp add local-llm -s user -- node /path/to/mcp-local-llm/dist/index.js工具（25 个）
allow_multiple
Allow multiple categories (default: false)
categories
(required): Array of possible categories
context
(required): Context and requirements
explain
Include explanation (default: false)
fields
(required): Array of fields to extract
focus
Specific aspect to emphasize
format
Output format (markdown, plain text, etc.)
instruction
(required): Transformation instructions
local_classify
Classify text into categories.
local_complete
Raw completion for maximum flexibility.
local_draft
Generate initial drafts for refinement.
local_extract
Extract structured information from text.
local_status
Check local LLM connection status and available models.
local_summarize
Summarize text using the local LLM.
local_transform
Transform text according to instructions.
max_length
Approximate max words (default: 150)
max_tokens
Max tokens (default: 2048)
output_format
"json" "yaml" "markdowntable"
prompt
(required): The prompt
style
"brief" "detailed" "bulletpoints" "executive"
system
System message
task
(required): What to draft
temperature
Temperature (default: 0.7)
text
(required): Text to summarize
tone
Desired tone (professional, casual, technical)