Skip to main content
Glama

AI PM Lab

by io.aipmlab
OverviewDiscussionsAdmin

Server Details

Learn how AI products work: lessons, cost calculators, real experiments, spec and eval guides.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL

TDQS

Score is being calculated.

Available Tools

11 tools
count_tokensCount tokens
Read-onlyIdempotent
Inspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
textYes
defineDefine an AI concept
Read-onlyIdempotent
Inspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
termYes
design_eval_suiteDesign an eval suite
Read-onlyIdempotent
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
featureNoWhat the AI feature does, who uses it, and what it must never do
estimate_costEstimate model cost
Read-onlyIdempotent
Inspect

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'.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelYes
cached_shareNoShare of input tokens served from the prompt cache, 0 to 1
input_tokensYes
output_tokensYes
requests_per_dayYes
get_lessonGet an AI PM Lab lesson
Read-onlyIdempotent
Inspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
slugYesThe lesson's slug, from search_lessons
list_challengesList AI PM Lab challenges
Read-onlyIdempotent
Inspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

list_experimentsList recorded experiments
Read-onlyIdempotent
Inspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
pageYesinjection (prompt injection defences), rag (retrieval), evals (graders), agent-loop, next-token, embeddings
prep_planning_meetingPrepare for an AI planning meeting
Read-onlyIdempotent
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
featureNoA few sentences about the AI feature
replay_experimentReplay a recorded experiment
Read-onlyIdempotent
Inspect

What happened in one recorded real run (e.g. whether a prompt injection leaked data with given defences), with a link to watch it in 3D.

ParametersJSON Schema
NameRequiredDescriptionDefault
runYesThe run's number from list_experiments
pageYesinjection (prompt injection defences), rag (retrieval), evals (graders), agent-loop, next-token, embeddings
review_ai_specReview an AI feature spec
Read-onlyIdempotent
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
specNoThe spec or PRD text
search_lessonsSearch AI PM Lab lessons
Read-onlyIdempotent
Inspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesA topic or question, e.g. 'how do I stop hallucinations'

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 11 tool updates
    • First observedcount_tokens
    • First observeddefine
    • First observeddesign_eval_suite
    • First observedestimate_cost
    • First observedget_lesson
    • First observedlist_challenges
    • First observedlist_experiments
    • First observedprep_planning_meeting
    • First observedreplay_experiment
    • First observedreview_ai_spec
    • First observedsearch_lessons

Related MCP Connectors

Related MCP Servers

  • Modelglass by Modelglass

    Modelglassofficial

    Modelglass
    A
    license
    Not graded
    quality
    A
    maintenance
    Live, sourced pricing and benchmark data across image, language, video, and audio AI models, seven tools for comparison, competitor lookups, and cost-aware routing. Also powers the free Modelglass VS Code extension.
    1
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources