io.aipmlab/ai-pm-lab

Est-ce que io.aipmlab/ai-pm-lab est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.aipmlab/ai-pm-lab » 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 18 outils

• compare_models≈ 694 tokens

  Compare several models side by side at a given volume: cost per request and per month, prices, context window, output limit, release date and knowledge cutoff, from AI Gateway's live catalog. Pass ids like 'openai/gpt-4.1-mini', or a provider name ('anthropic', 'openai', 'google') for its newest models, so you don't need to know which models are current.

  Paramètres, retour & exemple (5)

  Paramètres

  • models · array · requis
    Model ids like 'openai/gpt-4.1-mini', or provider names like 'anthropic' for that provider's newest models
  • cached_share · number · optionnel
    Share of input tokens served from the prompt cache, 0 to 1
  • input_tokens · integer · requis
    Input tokens per request: system prompt, retrieved documents, history and the user's message
  • output_tokens · integer · requis
    Output tokens per request: the length of a typical reply
  • requests_per_day · integer · requis
    Expected requests per day, for the monthly cost

  Exemple d'appel

  {"name": "compare_models", "arguments": {"models": [], "input_tokens": 1, "output_tokens": 1, "requests_per_day": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"models": [], "unknown": [], "live_catalog": true, "requests_per_day": 1}}

• count_tokens≈ 216 tokens

  Count the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).

  Paramètres, retour & exemple (1)

  Paramètres

  • text · string · requis
    The text to count, such as a system prompt or a typical user message

  Exemple d'appel

  {"name": "count_tokens", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tokens": 1, "tokenizer": "texte", "characters": 1}}

• define_term≈ 276 tokens

  A plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.

  Paramètres, retour & exemple (1)

  Paramètres

  • term · string · requis
    The AI term to define, e.g. 'RAG', 'temperature' or 'prompt caching'

  Exemple d'appel

  {"name": "define_term", "arguments": {"term": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• design_eval_suite≈ 289 tokens

  Build an evaluation suite for a planned AI feature with AI PM Lab's method: test cases (typical, edge, out of scope, attacks), graders with a judge rubric, pass bars, and a JSON test set. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · optionnel
    What the AI feature does, who uses it, and what it must never do

  Exemple d'appel

  {"name": "design_eval_suite", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• estimate_cost≈ 556 tokens

  What a model call costs per request, per day and per month at a given volume, from AI Gateway's live prices. Model ids look like 'openai/gpt-4.1-mini' or 'anthropic/claude-sonnet-4.5'.

  Paramètres, retour & exemple (5)

  Paramètres

  • model · string · requis
    A model id like 'openai/gpt-4.1-mini' or 'anthropic/claude-sonnet-4'
  • cached_share · number · optionnel
    Share of input tokens served from the prompt cache, 0 to 1
  • input_tokens · integer · requis
    Input tokens per request: system prompt, retrieved documents, history and the user's message
  • output_tokens · integer · requis
    Output tokens per request: the length of a typical reply
  • requests_per_day · integer · requis
    Expected requests per day, for the monthly cost

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"model": "texte", "per_day": 1, "per_month": 1, "input_share": 1, "per_request": 1, "price_source": "catalog", "prices_per_million": {}, "cache_saving_per_month": 1}}

• get_lesson≈ 394 tokens

  A lesson in full: the product decision it informs, its key idea and concepts, things to try with what to notice in each (from recorded runs), what a PM takes away and questions to ask engineers, with links to the lesson, its 3D tour and its challenge.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis · how-llms-work | writing-good-prompts | hallucination-and-grounding | embeddings-and-semantic-search | prompting-vs-rag-vs-fine-tuning | prompt-caching-and-cost | structured-outputs | how-ai-agents-work
    The lesson's slug, from search_lessons

  Exemple d'appel

  {"name": "get_lesson", "arguments": {"slug": "how-llms-work"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• list_challenges≈ 222 tokens

  The challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_challenges", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• list_experiments≈ 428 tokens

  The real runs recorded on one of AI PM Lab's 3D pages or lessons, each described by its setup (e.g. which defences or settings were on). Replay one to see what happened.

  Paramètres, retour & exemple (1)

  Paramètres

  • page · string · requis · injection | rag | evals | agent-loop | next-token | embeddings | how-ai-agents-work | how-llms-work
    A 3D page (injection, rag, evals, agent-loop, next-token, embeddings) or a lesson's slug (e.g. prompt-injection, model-routing, hallucination-and-grounding, human-in-the-loop)

  Exemple d'appel

  {"name": "list_experiments", "arguments": {"page": "injection"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• plan_ai_launch≈ 335 tokens

  A phased roadmap from where an AI feature is today to launch and its first month live: frame, prototype and model, evals, hardening, pilot, launch, monitoring. Each phase has exit criteria and the tests and checks for this feature, backed by findings from AI PM Lab's recorded real runs (injection, grounding, evals, agent cost). Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · optionnel
    What the AI feature does, who uses it, what it must never do, and where the work stands today

  Exemple d'appel

  {"name": "plan_ai_launch", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• prep_planning_meeting≈ 271 tokens

  The questions a PM should ask engineers about a planned AI feature, with why each matters and what a good answer sounds like. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · optionnel
    A few sentences about the AI feature

  Exemple d'appel

  {"name": "prep_planning_meeting", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• price_ai_feature≈ 303 tokens

  Work out an AI feature's unit economics and pricing: cost per request and per user (light, typical, heavy), levers like caching and routing, pricing options with margins, guardrails, and the assumptions to validate. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · optionnel
    What the feature does, the model it uses, expected usage, and how the product is priced today

  Exemple d'appel

  {"name": "price_ai_feature", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• quiz_me≈ 388 tokens

  A round from AI PM Lab's challenges, built from real recorded runs: Call It (predict what a model did), Spot the Failure (ship or flag a real output) or Which Wins? (pick the better of two setups). Returns the question without its answer; call again with the round id and the user's choice to mark it, see how players on the site called it, and get the next round.

  Paramètres, retour & exemple (3)

  Paramètres

  • game · string · optionnel · call-it | spot-the-failure | which-wins
    call-it, spot-the-failure or which-wins; any if left out
  • round · string · optionnel
    The id of the round the user is answering, from the last quiz_me result
  • answer · string · optionnel
    The user's choice for that round: its letter

  Exemple d'appel

  {"name": "quiz_me", "arguments": {"game": "call-it", "round": "texte", "answer": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• replay_experiment≈ 480 tokens

  What happened in one recorded real run (e.g. whether a prompt injection leaked data with given defences, or how many answers were made up without a facts sheet): the setup, each step, the result and the model's reply, with a link to run it on the site.

  Paramètres, retour & exemple (2)

  Paramètres

  • run · integer · requis
    The run's number from list_experiments
  • page · string · requis · injection | rag | evals | agent-loop | next-token | embeddings | how-ai-agents-work | how-llms-work
    A 3D page (injection, rag, evals, agent-loop, next-token, embeddings) or a lesson's slug (e.g. prompt-injection, model-routing, hallucination-and-grounding, human-in-the-loop)

  Exemple d'appel

  {"name": "replay_experiment", "arguments": {"run": 1, "page": "injection"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• review_ai_incident≈ 299 tokens

  A blameless post-incident review for an AI feature: where it failed (input, retrieval, prompt, model, tools, output checks), why evals and monitoring missed it, actions, and the new eval cases that would catch it next time. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • incident · string · optionnel
    What the feature does, what went wrong, and what's known so far

  Exemple d'appel

  {"name": "review_ai_incident", "arguments": {"incident": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• review_ai_spec≈ 284 tokens

  Check an AI feature spec or PRD against what AI PM Lab teaches: approach, model and cost, prompt, grounding, output contract, tools, security, human oversight, evals, monitoring, fallbacks. Gaps link to lessons. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • spec · string · optionnel
    The spec or PRD text

  Exemple d'appel

  {"name": "review_ai_spec", "arguments": {"spec": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• review_launch_readiness≈ 298 tokens

  A go/no-go review of an AI feature's launch plan: evals, grounding, attacks, approvals, cost, latency, monitoring, rollout and support, each marked ready, at risk or missing, with blockers and a launch-day watch list. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • plan · string · optionnel
    The feature, what was tested, and the launch plan

  Exemple d'appel

  {"name": "review_launch_readiness", "arguments": {"plan": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• search_lessons≈ 271 tokens

  Find AI PM Lab lessons on a topic (e.g. RAG, evals, agents, prompt injection, cost). Returns the best matches with their key idea and link.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    A topic or question, e.g. 'how do I stop hallucinations'

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

• write_acceptance_criteria≈ 312 tokens

  Acceptance criteria for an AI feature or user story that can actually be tested: Given/When/Then with measurable pass bars on a test set, must-pass safety criteria, latency and cost budgets, and example test cases, ready to paste into a ticket. Returns instructions to follow with the user's text.

  Paramètres, retour & exemple (1)

  Paramètres

  • feature · string · optionnel
    The AI feature or user story, who uses it, and what it must never do

  Exemple d'appel

  {"name": "write_acceptance_criteria", "arguments": {"feature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "links": []}}

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://aipmlab.io/api/mcp