thinkhard.SI

Use it inside your AI.

thinkhard.si runs an MCP server, the standard way AI assistants use outside tools. Add one address, and Claude, ChatGPT, Claude Code, Cursor or VS Code can find the right prompt in the repository, grade a prompt out of 10 and price an AI feature, in the middle of a conversation.

Server address https://thinkhard.si/mcp

Free, no account and no key. Nothing to install for the address above.

Add it to your assistant

  1. In Claude on the web or the desktop app, open Settings, then Connectors.
  2. Choose Add custom connector, name it thinkhard.si and paste https://thinkhard.si/mcp.
  3. In a chat, turn it on from the tools menu and ask, for example, “Find a thinkhard prompt for a cover letter and fill it in with my resume.”

Custom connectors depend on your Claude plan. The prompts also appear in the attachment menu, ready to fill in.

What your assistant can do with it

ToolWhat it doesRuns
search_promptsFinds ready-made prompts in the repository for a job, such as “meeting minutes” or “cancel a subscription”.Both
get_promptFetches one prompt with its blanks and why it works, and fills in the blanks you give it.Both
list_collectionsLists the repository’s collections and how many prompts each has.Both
grade_promptScores a prompt out of 10 on the ten checks and asks a plain question for each one it misses, exactly as the Grader does.Both
estimate_ai_costPrices a workload on every current model from the price index, per call and per month.Both
check_robot_speakFinds what makes a draft sound like AI, fixes the safe ones and writes instructions that stop them next time, like the Robot-Speak Checker.Local
fact_check_listLists every number, quote, source and link in an AI answer, riskiest first, like the Fact Check List.Local

Every prompt in the repository is also offered as an MCP prompt, with its blanks as the questions, so clients that support prompts show them as slash commands or in a menu.

Things to ask

  • “Find a thinkhard prompt for a performance self-assessment and fill it in from my notes.”
  • “Grade the prompt I just wrote with thinkhard, then fix what it says is missing.”
  • “What would 20,000 support replies a month cost on the cheapest models? Use thinkhard’s prices.”
  • “Before I send this, check it for robot-speak.” (local server)

The local server, for developers

The local server runs on your computer with Node 18 or later and has no dependencies. It runs the website’s own code for grade_prompt, check_robot_speak and fact_check_list, so the drafts you check never leave your machine, and it asks thinkhard.si only for the repository and prices.

Claude Code:

claude mcp add thinkhard -- npx -y --package=https://thinkhard.si/downloads/thinkhard-mcp.tgz thinkhard-mcp

Claude Desktop, Cursor, Windsurf and other clients that start a command:

{
  "mcpServers": {
    "thinkhard": {
      "command": "npx",
      "args": ["-y", "--package=https://thinkhard.si/downloads/thinkhard-mcp.tgz", "thinkhard-mcp"]
    }
  }
}

Download the package (version 1.0.0, about 30 KB) to read it first, or point the configuration at the saved file.

What reaches thinkhard.si

  • The server address. What your assistant sends with each call, such as your search words or the prompt to grade, is used to answer that call and is never stored or logged. We keep only a daily count of calls per tool. Your assistant’s own app sees the conversation as it always does.
  • The local server. Drafts and prompts you check stay on your computer. Only searches, prompt names and token counts for the repository and prices go to thinkhard.si.
  • The prompts. Free to use, change and run in your own work and your clients’ work. Please do not republish the collection or sell it (terms).

More in the privacy policy. For AI assistants that read websites, /llms.txt lists every page in plain text.