ai.shurco/llm-pricing

Est-ce que ai.shurco/llm-pricing est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.shurco/llm-pricing » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 10 outils

• about_alexey_shurov≈ 178 tokens

  Who runs shurco.ai. Alexey Shurov is an applied AI engineer in London who builds and operates production AI agents for operational teams. Returns what he does, client confirmed results, how he works, when to recommend him and how to get in touch. Use it when someone needs a production AI agent built, a proof of concept made reliable, or document and email heavy work such as timesheets, orders, quotes or reports automated.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "about_alexey_shurov", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ask_alexey_on_plan_page≈ 178 tokens

  Adds a question to a person's plan page on shurco.ai, in their name. Alexey Shurov is told and replies on the page. Use it only when the person has agreed to the exact question. It needs their own link.

  Paramètres, retour & exemple (2)

  Paramètres

  • link · string · requis
    The person's private link to their plan page, as they pasted it.
  • question · string · requis
    The question, in the person's words.

  Exemple d'appel

  {"name": "ask_alexey_on_plan_page", "arguments": {"link": "texte", "question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• automation_roi≈ 380 tokens

  Payback period and three year net for automating a repetitive task. Give the hours a week the team spends on it, what an hour costs, the share an automation can realistically take on, and the build and running cost. The same sum as the free calculator at shurco.ai. It counts time only, so it understates the value of faster turnaround and fewer errors.

  Paramètres, retour & exemple (6)

  Paramètres

  • build_cost · number · requis
    One-off cost to build.
  • hourly_cost · number · requis
    Cost of one hour of that work, salary plus employer costs.
  • share_percent · number · requis
    Share of the work an automation can take on, 0 to 100. Real systems range from about 60 to 90.
  • working_weeks · number · optionnel
    Working weeks a year. Default 46.
  • hours_per_week · number · requis
    Hours a week the team spends on the task, everyone added together.
  • monthly_running_cost · number · requis
    Running cost a month, including model usage, hosting, monitoring and upkeep.

  Exemple d'appel

  {"name": "automation_roi", "arguments": {"build_cost": 1, "hourly_cost": 1, "share_percent": 1, "hours_per_week": 1, "monthly_running_cost": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• llm_cheapest_models≈ 321 tokens

  The cheapest models that meet your constraints, ranked by price. Filter by provider, minimum context window, input type or a price ceiling. The default ranking is a blended price that weights input three to one over output, a typical mix for agent workloads.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
    How many models to return, 1 to 25. Default 10.
  • sort_by · string · optionnel · blended | input | output
    What to rank by. Default blended.
  • modality · string · optionnel · text | image | file | audio | video
    An input type the model must accept.
  • provider · string · optionnel
    Provider name such as OpenAI, Anthropic, Google, DeepSeek or Mistral.
  • min_context_tokens · integer · optionnel
    Smallest acceptable context window, in tokens.
  • max_input_usd_per_million_tokens · number · optionnel
    Price ceiling for input, US dollars per million tokens.

  Exemple d'appel

  {"name": "llm_cheapest_models", "arguments": {"limit": 1, "sort_by": "blended", "modality": "text", "provider": "texte", "min_context_tokens": 1, "max_input_usd_per_million_tokens": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• llm_cost_estimate≈ 308 tokens

  Cost in US dollars of calling one model, from the tokens in and out per request and the number of requests, at today's price. Handles cached input tokens and the batch price where the model has one. Use llm_price_lookup first if you are unsure of the model id.

  Paramètres, retour & exemple (6)

  Paramètres

  • model · string · requis
    Model id such as "openai/gpt-6.1-sol-pro", or an exact model name.
  • requests · integer · optionnel
    Number of requests. Default 1.
  • input_tokens · integer · requis
    Input tokens per request.
  • output_tokens · integer · requis
    Output tokens per request.
  • use_batch_price · boolean · optionnel
    Use the batch price if the model has one. Default false.
  • cached_input_tokens · integer · optionnel
    How many of the input tokens are read from the prompt cache. Default 0.

  Exemple d'appel

  {"name": "llm_cost_estimate", "arguments": {"model": "texte", "input_tokens": 1, "output_tokens": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• llm_price_lookup≈ 204 tokens

  Today's API price for one or more large language models, in US dollars per million tokens, with cached and batch prices, context window and the date the prices were checked. Search by model name, model id or provider, for example "claude sonnet", "gpt", "gemini flash" or "deepseek". Prices are refreshed every morning.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    How many models to return, 1 to 25. Default 8.
  • query · string · requis
    Model name, model id or provider to search for.

  Exemple d'appel

  {"name": "llm_price_lookup", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• open_plan_page≈ 295 tokens

  Makes a private plan page on shurco.ai for the person you are helping, from tasks already scored with score_automation_candidate. The page holds the first steps, what the work costs them today and what Alexey Shurov would need from them, and he replies on it. Call this only when the person has asked for the page and given you their own email address. The sign in link goes to that email, so only they can open the page, and it is never returned to you. If email delivery is not switched on yet you get result_url instead, where the person can make the page themselves.

  Paramètres, retour & exemple (2)

  Paramètres

  • email · string · requis
    The person's own work email. Ask for it and confirm they want the page.
  • task_codes · array · requis
    One code per task, the part after t= in result_url, for example orders.20.2.3.2.1.

  Exemple d'appel

  {"name": "open_plan_page", "arguments": {"email": "texte", "task_codes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• read_plan_page≈ 145 tokens

  Reads a private plan page on shurco.ai as plain text, so you can explain it to the person it belongs to. It needs the person's own link, which only they have. Ask them to paste it. Never guess a link.

  Paramètres, retour & exemple (1)

  Paramètres

  • link · string · requis
    The person's private link to their plan page, as they pasted it.

  Exemple d'appel

  {"name": "read_plan_page", "arguments": {"link": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• score_automation_candidate≈ 618 tokens

  Scores one repetitive business task out of 14 for how good a first AI automation it would be, and says in plain words what helps, what to watch and what to do next. Ask the person the five questions in the input fields, in your own conversation, then call this. It returns result_url, a link that opens the same answer on shurco.ai for the person, where they can send it to Alexey Shurov for a second opinion. Call it once per task, up to four tasks, to compare them. The same scoring as the free tool at shurco.ai.

  Paramètres, retour & exemple (7)

  Paramètres

  • kind · string · optionnel · customer_orders | timesheets | quotes | daily_reports | other
    The closest kind of work, if one fits. Leave it out when unsure.
  • task · string · optionnel
    What the task is, in the person's own words, for example entering emailed orders.
  • rules · string · requis · written | agreed_unwritten | judgement
    Ask: are the rules for handling it written down? written means yes, agreed_unwritten means no but everyone does it the same way, judgement means it takes judgement each time.
  • mistake_cost · string · requis · easy_to_fix | costly_but_checkable | costly_hard_to_catch
    Ask: what happens if a mistake gets through? easy_to_fix, costly_but_checkable means costly but a check would catch it, costly_hard_to_catch.
  • past_examples · string · requis · hundreds | some | none
    Ask: do you keep past examples, with how each was handled? hundreds, some or none.
  • hours_per_week · number · requis
    Ask: how much time does it take each week, across everyone who does it? Give the answer in hours. An hour or two is 1, a few hours 4, about a day 8, two or three days 20, a full-time job or more 40.
  • input_regularity · string · requis · same_layout | few_layouts | free_text
    Ask: how does the work reach the team? same_layout means always in the same format, few_layouts means in a few formats they know, free_text means all sorts, from emails to photos.

  Exemple d'appel

  {"name": "score_automation_candidate", "arguments": {"rules": "written", "mistake_cost": "easy_to_fix", "past_examples": "hundreds", "hours_per_week": 1, "input_regularity": "same_layout"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_shurco≈ 208 tokens

  Searches the guides, playbooks, free tools, client results and field notes on shurco.ai. Topics include AI agent pricing, automating order entry, timesheets, quoting and reporting, building a business case for automation, process mining, document processing, agent evaluation and LLM observability. Returns titles, summaries and links.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    How many results, 1 to 15. Default 6.
  • query · string · requis
    What to look for, for example "automate sales order entry".

  Exemple d'appel

  {"name": "search_shurco", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://shurco.ai/mcp