Diffusion LLM
Verified IntegrationClient Configuration
— Connect Diffusion LLM to Claude Desktop or Cursor in seconds{
"mcpServers": {
"diffusion-llm": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-diffusion-llm"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Provides a FastMCP fleet server for batch-speed local inference with diffusion language models, specifically designed for high-throughput workloads.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Diffusion LLM
It provides exceptional performance for diffusion models, achieving 200-400 tokens per second for local batch inference on hardware like the RTX 4090. This high throughput makes it ideal for data-intensive tasks.
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.