AI PM Lab MCP

An MCP server for AI Product Managers that provides access to lessons, model cost comparisons, and real experiments. It allows agents to look up AI concepts, estimate model costs, compare models, review feature specs, design evaluation suites, and quiz users on AI model behaviors using data from the AI PM Lab platform.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-18Operated by AI PM Lab

MCP endpoint (Streamable HTTP)

https://aipmlab.io/api/mcp

Vendor documentation

What you can do with it

Review an AI feature spec and identify missing components
Estimate model costs per request, day, and month
Design an evaluation suite for an AI support bot
Quiz users on AI model behaviors and concepts

Tools advertised by the last live check:

search_lessons
get_lesson
list_challenges
define_term
count_tokens
estimate_cost
compare_models
list_experiments
replay_experiment
quiz_me
review_ai_spec
prep_planning_meeting
design_eval_suite
write_acceptance_criteria
price_ai_feature
plan_ai_launch
review_launch_readiness
review_ai_incident

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add ai-pm-lab-mcp --url https://aipmlab.io/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-pm-lab-mcp in your MCP settings.

Cursor configuration

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

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

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-pm-lab-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http ai-pm-lab-mcp https://aipmlab.io/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

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

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

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

See all 1,015

Do you run AI PM Lab MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing