thinkhard.si prompt tools

Working · 3.2 s

si.thinkhard/prompt-toolsv1.1.0 Domain verified

Search 300+ expert prompt templates for work, grade a prompt out of 10, and price AI models.

AI & Agents

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://thinkhard.si/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

estimate_ai_cost Read-only

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 checked against each provider's pricing page. Give token counts, or paste the prompt text to estimate them.

modelsarray

Optional: model names or ids to include, such as "Claude Sonnet 5.5". Default: every current model.

prompt_textstring

Optional: the prompt, to estimate input tokens (about 4 characters a token).

input_tokensinteger

Input tokens per call. Omit to estimate from prompt_text.

output_tokensinteger

Output tokens per call.

calls_per_monthinteger

Tools (5)

Tool list last changed Oct 25, 2026.

estimate_ai_cost

read-only

Argument	Type	Description
models	array	Optional: model names or ids to include, such as "Claude Sonnet 5.5". Default: every current model.
prompt_text	string	Optional: the prompt, to estimate input tokens (about 4 characters a token).
input_tokens	integer	Input tokens per call. Omit to estimate from prompt_text.
output_tokens	integer	Output tokens per call.
calls_per_month	integer

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional: model names or ids to include, such as \"Claude Sonnet 5.5\". Default: every current model."
    },
    "prompt_text": {
      "type": "string",
      "description": "Optional: the prompt, to estimate input tokens (about 4 characters a token)."
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Input tokens per call. Omit to estimate from prompt_text."
    },
    "output_tokens": {
      "type": "integer",
      "default": 500,
      "minimum": 0,
      "description": "Output tokens per call."
    },
    "calls_per_month": {
      "type": "integer",
      "default": 1000,
      "minimum": 1
    }
  }
}

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 in each, and why it works. If the name does not match exactly, it answers with the closest matches instead. Pass values to fill blanks with the user's details. Ask the user for any blank you cannot fill from the conversation instead of inventing it.

read-only

Argument	Type	Description
prompt*	string	The slug, registry number or exact title from search_prompts.
values	object	Optional: blank name → the user's text, for example {"job_posting": "..."}.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "The slug, registry number or exact title from search_prompts."
    },
    "values": {
      "type": "object",
      "description": "Optional: blank name → the user's text, for example {\"job_posting\": \"...\"}.",
      "additionalProperties": {
        "type": "string"
      }
    }
  }
}

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, an example, what to do if unsure, layout for the model). Returns which checks pass and a plain question for each one that fails. Rule-based and instant; use it to see what a prompt is missing before improving it.

read-only

Argument	Type	Description
prompt*	string	The prompt to grade (the user message).
system	string	Optional system prompt, graded together with the prompt.
target	string	The model it is for. Layout is judged for this model.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "The prompt to grade (the user message)."
    },
    "system": {
      "type": "string",
      "description": "Optional system prompt, graded together with the prompt."
    },
    "target": {
      "enum": [
        "claude",
        "gpt",
        "gemini",
        "any",
        "agent",
        "midjourney",
        "image",
        "video"
      ],
      "type": "string",
      "default": "any",
      "description": "The model it is for. Layout is judged for this model."
    }
  }
}

list_collections

List the collections in the thinkhard.si prompt repository, with how many prompts each has.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

search_prompts

Find ready-made, expert prompt templates for a work task in the thinkhard.si repository (300+ prompts for email, meetings, presentations, job search, marketing, sales, support, HR, finance, legal, spreadsheets, research and more). Use it whenever the user wants to write, plan, summarize, analyze or draft something at work, before writing a prompt from scratch. Then call get_prompt with the slug.

read-only

Argument	Type	Description
limit	integer
model	string	Optional: only prompts laid out for this kind of model.
query*	string	What the user wants to do, in plain words, for example "cover letter" or "summarize a long contract". Everyday words, abbreviations (CV, 1:1, P&L, SOP) and typos are understood, and results come best match first.
collection	string	Optional: limit to one collection (see list_collections).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 8,
      "maximum": 25,
      "minimum": 1
    },
    "model": {
      "enum": [
        "claude",
        "gpt",
        "gemini",
        "any",
        "agent",
        "midjourney",
        "image",
        "video"
      ],
      "type": "string",
      "description": "Optional: only prompts laid out for this kind of model."
    },
    "query": {
      "type": "string",
      "description": "What the user wants to do, in plain words, for example \"cover letter\" or \"summarize a long contract\". Everyday words, abbreviations (CV, 1:1, P&L, SOP) and typos are understood, and results come best match first."
    },
    "collection": {
      "enum": [
        "office",
        "writing",
        "marketing",
        "careers",
        "sales",
        "support",
        "management",
        "people",
        "projects",
        "research",
        "data",
        "finance",
        "legal",
        "operations",
        "smallbiz",
        "education",
        "product",
        "engineering",
        "system",
        "media"
      ],
      "type": "string",
      "description": "Optional: limit to one collection (see list_collections)."
    }
  }
}