Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

effectsize

REMOTE · MCP.EFFECTSIZE.IO · 2 COMPONENTS

1,300+ real-world cases of how companies solved A/B testing, causal, recommender and ML problems

68 Trust /100

Last scanned (19 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 21 Nov 2026.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability52
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2882 tokens (~1441/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
  • Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 18 Nov 26 67

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.effectsize.io/mcp/public

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=effectsize.io CN=WE1,O=Google Trust Services,C=US 17 Nov 2026 15 Feb 2027 ECDSA 256 ECDSA-SHA256 86a7fa114dd74b2b0eb966d6ea3d7311
SANs: effectsize.io, mcp.effectsize.io, *.mcp.effectsize.io
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.effectsize.io. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
io. DS published 38690 8 Verified
effectsize.io. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.effectsize.io/mcp/public Verified 200
http (plaintext) http://mcp.effectsize.io/mcp/public HTTPS enforced 301 https://mcp.effectsize.io/mcp/public
MCP tools · 2 exposed · ~2,003 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_cards ~306

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.

NameTypeReqDescription
max_tokensinteger–Approximate cap on the response size; long sections are truncated.
offsetinteger–Character offset for the talk section.
search_idstring–search_id of the search these cases came from (for logging relevance).
sectionsarray–Card sections to return; default: problem, solution, core_idea, results, limitations. 'talk' = full transcript, paged with offset.
slugsarrayyesCase slugs from search_cases results (the `slug` field).

No output schema declared.

No examples provided.

search_cases ~1,697

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.

NameTypeReqDescription
constraintsobject–Conditions that make the problem hard. `must` = essential to the user's situation (strong boost, not a filter); `nice` = likely or partly true. adversarial-behavior: actors adapt to the system: fraud…
exclude_slugsarray–Cases already seen.
filtersobject–Hard filters. Use only when the user asked for them.
industrystring–The user's industry, if known. Boost only, never a filter.
keywordsarray–Short English keywords and synonyms likely to appear in a case.
limitinteger–How many cases to return (ranked).
method_hintsarray–Methods that could solve it, if you know them (e.g. 'CUPED', 'switchback', 'synthetic control', 'uplift modeling', 'two-tower'). Optional; leave empty rather than guess wildly.
phrasingsarrayyes2–4 different English formulations of the problem: one in plain words, one in practitioner jargon, one as 'How to …'.
prev_search_idstring–search_id of the previous search when refining.
problem_summarystring–Optional. 1–3 sentences: the clarified problem, anonymized. Stored by the archive to learn which problems people bring.
taskstringyesThe problem in one or two English sentences, abstract: what must be decided or built and what makes it hard. No company, product or internal numbers.
task_typesarray–1–2 task types. analyze-user-behavior: describe how users behave: funnels, paths, retention, cohorts, engagement, journeys; answer-questions-over-data: let people ask questions of structured data in…

No output schema declared.

No examples provided.

Install

How do I install the effectsize MCP server?

effectsize is a hosted endpoint at https://mcp.effectsize.io/mcp/public, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.effectsize.io

# add to Claude Code
claude mcp add --transport http vzhyvov-effectsize 'https://mcp.effectsize.io/mcp/public'
Common questions

What is the effectsize MCP server?

effectsize is an MCP server listed in the public MCP registry as io.github.vzhyvov/effectsize. 1,300+ real-world cases of how companies solved A/B testing, causal, recommender and ML problems. This page covers its hosted endpoint (https://mcp.effectsize.io/mcp/public).

Is the effectsize MCP server safe to use?

effectsize scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the effectsize MCP server expose?

effectsize exposes 2 tools: search_cases, get_cards. Their descriptions and schemas cost roughly 2,003 tokens of context every time the server is loaded.

Does the effectsize MCP server require authentication?

No. We connected to effectsize without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the effectsize MCP server still maintained?

effectsize is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the effectsize MCP server?

VerifyMCP ran 13 checks on effectsize, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.