# AI PM Lab

> AI PM Lab is a free MCP server for education and exams. Free lessons, live model cost comparison and eval design help for AI product managers. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** Web, API
- **Website:** https://aipmlab.io/mcp
- **MCP Registry name:** io.aipmlab/ai-pm-lab
- **Categories:** education and exams, AI models and LLM tooling
- **Listing updated:** 2026-11-16

## About

Teaching material is the backbone: lessons with a key idea and things to try, a glossary of 60+ AI concepts and challenges with leaderboards. Hundreds of recorded real model runs, such as prompt-injection defences and model routing, can be listed, replayed step by step and turned into quiz rounds marked by the server.

The number-crunching tools count tokens (nothing sent is kept), estimate cost per request, day and month with prompt caching, and compare current models by cost, context window, release date and knowledge cutoff using a live catalog. Prompt-style helpers review an AI feature spec, prepare questions for a planning meeting, design an eval suite, write acceptance criteria, price a feature and plan a launch.

The connector is free, open and read-only, with no sign-in. Answers link back to the site where ideas can be tried with real models.

## Features

- **Lessons and glossary:** Look up lessons and 60+ concept definitions.
- **Cost estimates:** Per-request, daily and monthly cost with caching.
- **Model comparison:** Compare models on cost, context and cutoff.
- **Recorded experiments:** Replay real runs step by step.
- **Quizzes:** Rounds marked by the server.
- **PM prompts:** Spec review, eval design, pricing and launch plans.

## Good for

- Price an AI feature at expected volume
- Review a feature spec for gaps
- Design an eval suite for a support bot
- Learn what a concept like LLM-as-judge means

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http ai-pm-lab https://aipmlab.io/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://aipmlab.io/api/mcp
```

### Cursor (~/.cursor/mcp.json)

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

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

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

## Tools

- `search_lessons`: Find lessons on a topic
- `get_lesson`: Details of one lesson
- `define_term`: Plain-language AI definitions
- `list_challenges`: Challenges and leaderboards
- `count_tokens`: Count tokens in text
- `estimate_cost`: Estimate model cost at volume
- `compare_models`: Compare models side by side
- `list_experiments`: List recorded experiments
- `replay_experiment`: Replay one recorded run
- `quiz_me`: Quiz rounds from real runs
- `review_ai_spec`: Review an AI feature spec
- `prep_planning_meeting`: Questions for a planning meeting
- `design_eval_suite`: Build an eval suite
- `write_acceptance_criteria`: Testable acceptance criteria
- `price_ai_feature`: Unit economics and pricing options
- `plan_ai_launch`: Roadmap to launch

## FAQ

### Is sign-in needed?

No, it is free, open and read only.

### Is my text stored?

count_tokens says nothing you send is kept.

### Which clients?

Claude, ChatGPT, Cursor, VS Code and other remote MCP clients.

### Where do prices come from?

A live model catalog.

### Is AI PM Lab free?

Yes. AI PM Lab is free to use.

### How do I add AI PM Lab to Claude Code?

Run this command in your terminal: claude mcp add --transport http ai-pm-lab https://aipmlab.io/api/mcp

### What are the best alternatives to AI PM Lab?

The closest alternatives to AI PM Lab are Claude Code Ultimate Guide, Born Then, FreeDict, signafAIde and Toolkien.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Born Then](https://ai-powered.com/mcp/born-then): Born Then is a free MCP server for education and exams.
- [FreeDict](https://ai-powered.com/mcp/freedict): FreeDict is a freemium MCP server for language learning.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/ai-pm-lab
