Skip to content

AI PM Lab MCP server

io.aipmlab/ai-pm-labaipmlab.iostreamable-httpv1.2.0Scanned

Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.

18 tools: 12 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 12 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

12 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AI PM Lab MCP server can do

The AI PM Lab MCP server is published by aipmlab.io, a domain the MCP Registry verified. It has 18 tools. It can create or change data (12 tools: define_term, estimate_cost, replay_experiment, quiz_me and 8 more), but cannot delete data. 6 tools only read.

2 tools bring in text other people can write (estimate_cost and compare_models).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 15, 2026, version 1.2.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

18 tools

Changes things 12Claude Code: ask
  • define_termA plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    A plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Define an AI concept
  • design_eval_suiteBuild 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 te…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Design an eval suite
  • estimate_costWhat a model call costs per request, per day and per month at a given volume, from AI Gateway's live prices.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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'.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Estimate model cost
  • plan_ai_launchA 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Plan an AI feature's road to launch
  • prep_planning_meetingThe questions a PM should ask engineers about a planned AI feature, with why each matters and what a good answer sounds like.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Prepare for an AI planning meeting
  • price_ai_featureWork 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, guardrail…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Price an AI feature
  • quiz_meA 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?No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Quiz me on real AI results
  • replay_experimentWhat happened in one recorded real run (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Replay a recorded experiment
  • review_ai_incidentA 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 ne…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Write up an AI incident
  • review_ai_specCheck 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, f…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Review an AI feature spec
  • review_launch_readinessA 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 …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Review an AI feature's launch readiness
  • write_acceptance_criteriaAcceptance 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 cos…1 finding

    Why it is in this group

    • The name "write_acceptance_criteria" says "write": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "write_acceptance_criteria" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "write_acceptance_criteria" says "write": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Write acceptance criteria for an AI feature
Only reads 6Show 6 read-only tools
  • compare_modelsCompare 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 li…Reads text others writeNo findings

    Why it is in this group

    • The name "compare_models" says "compare": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Compare models
  • count_tokensCount the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).No findings

    Why it is in this group

    • The name "count_tokens" says "count": a word for reading.
    Description, as the server wrote it
    Count the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Count tokens
  • get_lessonA 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 …No findings

    Why it is in this group

    • The name "get_lesson" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get an AI PM Lab lesson
  • list_challengesThe challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.No findings

    Why it is in this group

    • The name "list_challenges" says "list": a word for reading.
    Description, as the server wrote it
    The challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List AI PM Lab challenges
  • list_experimentsThe real runs recorded on one of AI PM Lab's 3D pages or lessons, each described by its setup (e.g.No findings

    Why it is in this group

    • The name "list_experiments" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List recorded experiments
  • search_lessonsFind AI PM Lab lessons on a topic (e.g.No findings

    Why it is in this group

    • The name "search_lessons" says "search": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Search AI PM Lab lessons

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:55 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
12
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 12 tools that change things (12 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://aipmlab.io/api/mcp: tools/list returned 18 tools to an anonymous client, including define_term (write), estimate_cost (write), replay_experiment (write), quiz_me (write), review_ai_spec (write) and 7 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "write_acceptance_criteria" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "write_acceptance_criteria" says "write": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 changed.~3 changedView diff
  2. Tools18 changed.~18 changedView diff

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ai-pm-lab__search_lessons",
      "mcp__ai-pm-lab__get_lesson",
      "mcp__ai-pm-lab__list_challenges",
      "mcp__ai-pm-lab__count_tokens",
      "mcp__ai-pm-lab__compare_models",
      "mcp__ai-pm-lab__list_experiments"
    ],
    "ask": [
      "mcp__ai-pm-lab__define_term",
      "mcp__ai-pm-lab__estimate_cost",
      "mcp__ai-pm-lab__replay_experiment",
      "mcp__ai-pm-lab__quiz_me",
      "mcp__ai-pm-lab__review_ai_spec",
      "mcp__ai-pm-lab__prep_planning_meeting",
      "mcp__ai-pm-lab__design_eval_suite",
      "mcp__ai-pm-lab__write_acceptance_criteria",
      "mcp__ai-pm-lab__price_ai_feature",
      "mcp__ai-pm-lab__plan_ai_launch",
      "mcp__ai-pm-lab__review_launch_readiness",
      "mcp__ai-pm-lab__review_ai_incident"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ai-pm-lab. Review it before you use it.

Capability tags behind 2 rules
  • mcp__ai-pm-lab__estimate_cost untrusted-input
  • mcp__ai-pm-lab__compare_models untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.aipmlab/ai-pm-lab/verify?hash=25340c32ebe693b4d79b585901712c36ab18cc4e145a0e73232d725ba4a4e2cc" | jq -e '.changed == false'

Pinned hash 25340c32ebe6, from Nov 15, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.aipmlab/ai-pm-lab/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.aipmlab/ai-pm-lab
[![Anlyon Radar](https://radar.anlyon.com/badge/io.aipmlab/ai-pm-lab.svg)](https://radar.anlyon.com/servers/io.aipmlab/ai-pm-lab)

Source: MCP Registry. Synced Oct 21, 2026, 18:13 UTC.

AI PM Lab MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AI PM Lab MCP server safe?

No scan can promise that. What its definitions show: 18 tools, 12 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AI PM Lab MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AI PM Lab MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the AI PM Lab MCP server have?

18 tools: 12 write, 6 read. define_term, estimate_cost, replay_experiment, quiz_me, review_ai_spec, prep_planning_meeting, design_eval_suite, write_acceptance_criteria and 10 more.

Does the AI PM Lab MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AI PM Lab MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the AI PM Lab MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.