effectsize
Server Details
1,300+ real-world cases of how companies solved A/B testing, causal, recommender and ML problems
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- vzhyvov/effectsize-skill
- GitHub Stars
- 1
- Server Listing
- effectsize
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools form an unambiguous search-then-read pipeline: search_cases finds candidate cases and returns compact passports, while get_cards opens specific cards by section. Descriptions explicitly state the ordering ('Call this first', 'Open cards with get_cards'), leaving no realistic chance of misselection.
Both names follow the same verb_noun snake_case convention (search_cases, get_cards) with verbs that accurately reflect the search vs. retrieval semantics. No deviation or mixed-style naming anywhere in the surface.
Two tools is on the thin side of the 3-15 guideline, but for a read-only case-study archive the search+fetch pair is the minimal complete pattern and each tool clearly earns its place. No redundant or filler tools are present.
Discovery (search_cases with facets, missing_must hints) and consumption (get_cards with selectable sections, offset paging, materials metadata) are both covered for a read-only archive. The only gap is that original materials must be fetched by the user, and there is no way to enumerate or browse the archive without a query.
Available Tools
2 toolsget_cardsRead casesARead-onlyInspect
Read up to 5 cases found by search_cases. Pick sections to save context: problem, solution, tools,
core_idea, how_to_apply, code, results, limitations, talk (full edited transcript of a talk, paged with offset).
Default: problem, solution, core_idea, results, limitations (~1k tokens per card); ask for how_to_apply / code when the user is going to
implement. Open about 3 cards per call; the response is capped by max_tokens (default 5000). Every card also returns materials:
the original (url, format, language, access: open | video | paywall | bot-blocked | offline, with a note on how to
get it), the transcript if there is one, code repositories, slides and other extras. Use them as described in the
server instructions; ask the user to fetch an original you cannot access.
Inputs: slugs (required), offset, sections, search_id, +1 more.
search_casesSearch casesARead-onlyInspect
effectsize: real-world case studies of how companies (Netflix, Uber, Airbnb, DoorDash, Meta and hundreds more) solved
product analytics, experimentation, causal, recommendation, search, ML and LLM-in-analytics problems. Call this first,
before answering from general knowledge, whenever the user asks how to solve such a problem or how others did it, and
whenever the user mentions effectsize.
Find cases in the archive that solve the user's problem. Deterministic search (no LLM on the server): it matches
your structured description against the cards' closed vocabularies (task type, constraints, methods) and runs keyword
search over each phrasing. Write everything in English, abstractly, without the user's company or confidential data.
Returns compact passports (why each case matched, which must constraints the case lacks (missing_must), has: code / transcript /
slides / extras available), facets of the candidate
set and hints when few cases match all required constraints. Open cards with get_cards.
Inputs: task (required), phrasings (required), limit, filters, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.
Open data: 1,590 JTBD hypotheses with cold-traffic test results and cost per lead. CC BY 4.0
Causal analytics: ask a business question, get a deterministic causal answer and charts.
Independent weekly on AI in B2B revenue teams: articles, frameworks, skills, playbooks, datasets.
Related MCP Servers
- AlicenseAqualityBmaintenanceMarketing, Search, AI & Machine Learning (Dockerfile is present)897 npmMIT
- FlicenseNot gradedqualityBmaintenanceRun conjoint experiments and causal research through AI powered behavioral simulations5-
- AlicenseCqualityDmaintenanceEnables evidence-backed business decisions by connecting questions to experiment and metric data, applying statistical analyses, and producing rollout, hold, or investigate verdicts with reproducible audit traces.500MIT
- FlicenseNot gradedqualityBmaintenanceCross-source attribution across 37+ business tools. True ROAS in 14 seconds. Not a dashboard. A decision.29-
Glama MCP Gateway
Add one secure layer between your agents and this server.