max_tokens
Max tokens (default: 2048)
How to use it
max_tokens is exposed by the MCP Local Llm MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the max_tokens tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install MCP Local Llm
claude mcp add local-llm -s user -- node /path/to/mcp-local-llm/dist/index.jsOther tools in MCP Local Llm (24)
Allow multiple categories (default: false)
(required): Array of possible categories
(required): Context and requirements
Include explanation (default: false)
(required): Array of fields to extract
Specific aspect to emphasize
Output format (markdown, plain text, etc.)
(required): Transformation instructions
Classify text into categories.
Raw completion for maximum flexibility.
Generate initial drafts for refinement.
Extract structured information from text.
Check local LLM connection status and available models.
Summarize text using the local LLM.
Transform text according to instructions.
Approximate max words (default: 150)
"json" "yaml" "markdowntable"
(required): The prompt
"brief" "detailed" "bulletpoints" "executive"
System message
(required): What to draft
Temperature (default: 0.7)
(required): Text to summarize
Desired tone (professional, casual, technical)