Lm-Resizer
Verified IntegrationClient Configuration
— Connect Lm-Resizer to Claude Desktop or Cursor in seconds{
"mcpServers": {
"lm-resizer": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-lm-resizer"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Filters and compresses noisy tool output from AI agents to reduce token waste and improve LLM reasoning, ensuring full evidence is recoverable.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Lm-Resizer
Even with large context windows (e.g., 200K, 1M+), noisy output incurs significant costs per token, increases latency due to more data processing, and causes 'attention dilution' where critical information gets lost. Lm-Resizer focuses on signal density to combat these issues.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.