Learning Resources

aipmlab.io

An MCP server for AI PM Lab that provides lessons, challenges, concept definitions, and token counting utilities to learn about AI product management.

1 endpoint11 known toolsFirst detected October 11, 2026Last detected October 11, 2026

ENDPOINT 1

https://aipmlab.io/api/mcp

No auth detected

MCP server metadata

Name: ai-pm-lab
Version: 1.0.1

Capabilities

tools.listChangedprompts.listChangedresources.listChanged

Server instructions

AI PM Lab (aipmlab.io) teaches product managers how AI products work, with interactive lessons that run real models, 3D tours and challenges. Use these tools to look up lessons and concepts, count tokens and estimate model costs, replay recorded real experiments, and to review AI feature specs, prepare for planning meetings and design eval suites. Answers end with links to the site; keep them, since that's where the user can try each idea hands-on. Free to use.

Known tools 11

search_lessons

Find AI PM Lab lessons on a topic (e.

Inferred read-only

get_lesson

A lesson's key idea, concepts, things to try and suggested prompts, with links to the lesson, its 3D tour and its challenge.

Inferred read-only

list_challenges

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

Inferred read-only

define

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

Inferred read-only

count_tokens

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

Inferred read-only

estimate_cost

What a model call costs per request, per day and per month at a given volume, from AI Gateway's live prices.

Inferred read-only

list_experiments

The real runs recorded on one of AI PM Lab's 3D pages, each described by its setup.

Inferred read-only

replay_experiment

What happened in one recorded real run (e.

Inferred read-only

review_ai_spec

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.

Inferred read-only

prep_planning_meeting

The questions a PM should ask engineers about a planned AI feature, with why each matters and what a good answer sounds like.

Inferred read-only

design_eval_suite

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ai-pm-lab]
url = "https://aipmlab.io/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ai-pm-lab": {
      "type": "http",
      "url": "https://aipmlab.io/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ai-pm-lab
Remote MCP URL: https://aipmlab.io/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ai-pm-lab": {
      "url": "https://aipmlab.io/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "ai-pm-lab": {
      "type": "http",
      "url": "https://aipmlab.io/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "ai-pm-lab",
  "transport": "streamable-http",
  "url": "https://aipmlab.io/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for aipmlab.io was fetched 2026-10-12T08:38:32.742Z.

Trust status Neutral

aipmlab.io is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.