si.thinkhard/prompt-tools

up checked 2026-11-11T09:39:45.583Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

thinkhard.si prompt tools

Publisher-provided description

669 work prompts, prompt and answer checks, a job planner, a prompt linter and AI prices.

Summary by lookupd

Searches, grades, lints and estimates costs for AI prompts, plus plans workflows and defines AI terms from a prompt library.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http prompt-tools https://thinkhard.si/mcp

Codex, remote (streamable-http)

codex mcp add prompt-tools --url https://thinkhard.si/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "prompt-tools": {
      "url": "https://thinkhard.si/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (14 tools)

Publisher-provided text

• search_prompts Search the thinkhard.si repository of 1,024 tested prompt templates for work tasks: email, meetings, presentations, job search, marketing, sales, support, HR, f
• get_prompt Get the full text of one prompt from the thinkhard.si repository by its slug, registry number (such as CAR-001) or exact title, with its {{blanks}}, what goes i
• list_collections List the collections in the thinkhard.si prompt repository, with how many prompts each has.
• grade_prompt Score a prompt out of 10 on the ten checks thinkhard.si uses (what to make, who it is for, background facts, length, format, what to avoid, what good looks like
• estimate_ai_cost Estimate the monthly cost of running a prompt on current AI models (Claude, GPT, Gemini, DeepSeek, Qwen and others), from thinkhard.si's price catalog, which is
• fix_bad_answer When an AI answer goes wrong (it made up a source or a number, ignored an instruction, came back too long or in the wrong shape, sounded robotic or generic, cha
• get_prompt_pattern The 24 prompt patterns from thinkhard.si: small moves that change the answer, such as giving the facts, naming the reader, showing one example, setting a length
• define_ai_term Plain-English definitions of 102 AI words from the thinkhard.si glossary (token, context window, hallucination, temperature, system prompt, RAG, fine-tuning, ag
• check_answer Did the AI do what the prompt asked? Give the prompt and the answer it got. Finds every rule in the prompt that can be checked by reading (length in words, char
• build_assistant Write the instructions for an assistant that keeps its rules: a ChatGPT custom GPT, a Claude Project, a Gemini Gem, a Microsoft Copilot agent or an app's system
• plan_workflow Turn a job such as hiring for a role, launching a feature, closing the month or applying for a job into steps in the order the work happens, each with the exper
• lint_prompts Find the prompts in source files (Python, JavaScript, TypeScript, YAML, JSON and prompt files) and review each for what breaks AI features in production: user i
• audit_library Read many prompts at once, such as a team's shared prompt doc: each prompt's score on the ten checks, the task it does and how ready it is for it, near-copies w
• check_agent_brief Before a task goes to a coding agent (Claude Code, Codex, Cursor, GitHub Copilot or another), check the brief: what kind of task it is, which of the parts that

Details

• Version: 1.3.0
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 553 ms
• First indexed: 2026-11-01T10:08:49.732Z
• Last seen in registry: 2026-11-04T17:17:21.168Z
• Website: https://thinkhard.si/developers/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/si.thinkhard/prompt-tools.svg)](https://lookupd.com/servers/si.thinkhard/prompt-tools)

• 62092 servers
• Last crawl: 2026-11-11T17:38:11.606Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp