Kiki Compressor
Verified IntegrationClient Configuration
— Connect Kiki Compressor to Claude Desktop or Cursor in seconds{
"mcpServers": {
"kiki-compressor": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-kiki-compressor"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Compresses query-aware context for large language models, significantly reducing input tokens and latency while maintaining answer quality.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Kiki Compressor
Kiki Compressor is an OpenAI API compatible proxy designed to significantly reduce the input tokens and latency for large language models. It achieves this by intelligently compressing query-aware context, eliminating irrelevant information while statistically maintaining answer quality, saving costs and improving performance.
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.