AI PM Lab is listed as active in the registry but did not answer our last check. It exposes 18 tools.
Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.
Uptime history
30 days of history · worst day 0%
30 days agonow
2.2%
Uptime 24h
2 of 92 checks
18
Tools
read from the server
306 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 25
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 12 October 2026. No other catalogue keeps this.
6 Nov
3 tools changed the parameters they ask for
get_lesson, list_experiments, replay_experiment
17 Oct
4 tools appeared
define_term, plan_ai_launch, review_ai_incident and 1 more
17 Oct
3 tools changed the parameters they ask for
compare_models, count_tokens, estimate_cost
17 Oct
3 tools disappeared
ai_incident_review, define, launch_readiness_review
17 Oct
2 tool descriptions were rewritten
get_lesson, quiz_me
12 Oct
6 tools appeared
ai_incident_review, compare_models, launch_readiness_review and 3 more
12 Oct
2 tool descriptions were rewritten
list_experiments, replay_experiment
12 Oct
2 tools changed the parameters they ask for
list_experiments, replay_experiment
AI PM Lab does not always answer
Over the last week it answered 3.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
run in your terminal
claude mcp add ai-pm-lab --transport http https://aipmlab.io/api/mcpSettings → Connectors → Add custom connector, then paste this address
https://aipmlab.io/api/mcp~/.codex/config.toml
[mcp_servers.ai-pm-lab]
url = "https://aipmlab.io/api/mcp".cursor/mcp.json
{
"mcpServers": {
"ai-pm-lab": {
"url": "https://aipmlab.io/api/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"ai-pm-lab": {
"type": "http",
"url": "https://aipmlab.io/api/mcp"
}
}
}Available tools 18
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
review
review_ai_incident
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.
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. Gaps link to lessons. Returns instructions to follow with the user's text.
review_launch_readiness
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.
acceptance
write_acceptance_criteria
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.
challenges
list_challenges
The challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.
compare
compare_models
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.
count
count_tokens
Count the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).
define
define_term
A plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.
design
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. Returns instructions to follow with the user's text.
estimate
estimate_cost
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'.
experiments
list_experiments
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.
lesson
get_lesson
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.
lessons
search_lessons
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.
plan
plan_ai_launch
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.
prep
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. Returns instructions to follow with the user's text.
price
price_ai_feature
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.
quiz
quiz_me
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.
replay
replay_experiment
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.
Tools removed
Tools this server used to expose. Anything built against them stopped working on the day they went.
ai_incident_review
removed 17 Oct 2026
define
removed 17 Oct 2026
launch_readiness_review
removed 17 Oct 2026
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://aipmlab.io/api/mcp | streamable-http | answering | 82 ms | 0 min ago |
Alternatives to AI PM Lab
same job, measured the same wayAI Video Atlas
by aivideoatlas
Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.
Modelpulse
by cloudcorprecords
AI model releases, price changes, comparisons and cost estimates in one normalised feed.
Ai Model Experiments
by pipeworx-io
AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…
Inferenceindexer MCP
by desmartin01
AI inference pricing for agents: live and historical model prices, provider comparison.
Untax
by mooshee
Research county property assessments and prepare draft comparisons. (mooshworks.com)
Commerce
by lmk
Cross-merchant product search with real price history, comparisons, and demand signals.
GunsNPrices
by gunsnprices
Parse gun and ammo titles (model, caliber, cost per round); find GunsNPrices price comparison pages
Bike4Mind — the open-core AI workbench
by bike4mind
Read-only facts on Bike4Mind: live model catalog, comparisons, open-core license, blog, updates.
AI PM Lab — questions
Answers built from our own checks of this server.
What can AI PM Lab do?
It exposes 18 tools, read directly from the server on our last check. Among them: compare_models, count_tokens, define_term, design_eval_suite, estimate_cost, get_lesson and 12 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is AI PM Lab working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 2 of 92 checks got a reply (2.2%), average response time 306 ms. The bar chart above shows every period we have measured.
Did AI PM Lab ever remove tools?
Yes. ai_incident_review, define, launch_readiness_review are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
The registry lists AI PM Lab as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect AI PM Lab?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AI PM Lab need an API key?
No. AI PM Lab completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 18 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AI PM Lab?
It answers our handshake in 306 ms on average, which is faster than 45% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.