
AgentReady
Send fewer tokens to your LLM: MCP, gateway and API
128 followers
Send fewer tokens to your LLM: MCP, gateway and API
128 followers
AgentReady trims what you send to LLMs. An MCP server gives Claude, Cursor and Windsurf tools to compress long context, read any URL as clean Markdown and shrink JSON into TOON. A self-hosted gateway and a REST API do the same for your apps.
This is the 2nd launch from AgentReady. View more

AgentReady MCP
Launching today
New: AgentReady now works inside your AI assistant. One MCP server (npx agentready-cloud-mcp) gives Claude Code, Cursor and Windsurf three tools: compress long context before it is read, open any URL as clean Markdown instead of raw HTML, and shrink JSON into TOON. Building an app? The new self-hosted gateway squeezes every OpenAI and Anthropic call while your API key never leaves your machine. Free during beta.





Free
Launch Team

AWS Activate CreditsCredits that fuel your startupβs next milestone
Promoted


Hey Product Hunt! π Christian here.
In February you took AgentReady to #9 of the day. Since then you've pushed 2.1M+ tokens through it across 10,000+ API calls, and 1.2M of those tokens never hit an LLM bill. Thank you π
Today AgentReady moves to where you actually work: inside your AI assistant.
π§© AgentReady MCP (one command, free):
claude mcp add agentready -e AGENTREADY_API_KEY=ak_β¦ -- npx -y agentready-cloud-mcp
Works in Claude Code, Claude Desktop, Cursor, Windsurf and any MCP client:
βοΈ tokencut_compress: long context loses greetings, hedges and filler before the model reads it. Code, URLs and numbers stay untouched.
π url_to_markdown: your agent reads the article, not the navbar. In our own usage 903K tokens of HTML became 14K of Markdown.
π§± json_shrink: API responses become TOON. 30 order objects went from 1,106 to 444 tokens.
π Building an app? Run the gateway yourself: npx agentready-cloud-gateway, then point your OpenAI or Anthropic SDK at localhost. Only message text is sent to us for compression; your provider key and the answers never leave your machine. Hacker News asked for exactly this, thank you nateb2022 and nevon.
Your comments built this release:
βCan I see what was trimmed?β Every response reports tokens before and after, and the dashboard has a shareable savings receipt.
βWhat about output tokens?β The output lever (lite / caveman / ultra) makes the model answer tersely.
Free during the beta. There's a small box in the dashboard asking what you'd pay: your answer sets the price.
Tell me: which assistant should we support next, and where do your tokens go: context, web pages, JSON or answers?
I'll be here all day. Also on X: x.com/christalingx π