InferBench
Verified IntegrationClient Configuration
— Connect InferBench to Claude Desktop or Cursor in seconds{
"mcpServers": {
"inferbench": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-inferbench"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Automate the download, setup, and benchmarking of local LLM inference engines and cloud APIs with real-time performance metrics.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for InferBench
InferBench is a developer tool that automates the entire pipeline for local LLM inference: downloading engines/models, setting up optimal configurations, benchmarking performance, and serving models via MCP with a single click.
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.