Skip to main content
Glama

Disco

표 형식 데이터에서 통계적으로 검증된 새로운 패턴을 찾아보세요 — 인간과 에이전트가 놓치는 특성 상호작용, 하위 그룹 효과 및 조건부 관계를 발견합니다.

PyPI License: MIT

Leap Laboratories에서 제작했습니다.


실제 기능

대부분의 데이터 분석은 질문에서 시작하지만, Disco는 데이터에서 시작합니다.

편향이나 가정 없이, 대상 열을 유의미하게 변화시키는 특성 조건의 조합을 찾아냅니다. 예를 들어, "HDL이 낮고 CRP가 높은 45~65세 환자는 재입원율이 3배 높다"와 같은 결과를 해당 상호작용을 미리 가설로 세우지 않아도 찾아낼 수 있습니다.

각 패턴은 다음과 같은 특징을 가집니다:

  • 홀드아웃 세트에서 검증됨 — 일반화 가능성을 높입니다.

  • FDR 보정됨 — 다중 검정을 위해 조정된 p-값이 포함됩니다.

  • 학술 문헌과 대조 확인 — 발견한 내용을 이해하고 새로운 것인지 식별하는 데 도움을 줍니다.

출력은 조건, 효과 크기, p-값, 인용문 및 발견된 모든 패턴에 대한 참신성 분류로 구조화되어 있습니다.

다음과 같은 경우에 사용하세요: "X와 관련하여 가장 중요한 변수는 무엇인가?", "우리가 놓치고 있는 패턴이 있는가?", "이 데이터로 어디서부터 시작해야 할지 모르겠다", "A와 B가 C에 어떤 영향을 미치는지 이해해야 한다".

다음 용도로는 적합하지 않음: 요약 통계, 시각화, 필터링, SQL 쿼리 — 이러한 작업에는 pandas를 사용하세요.


Related MCP server: Discovery Engine MCP Server

빠른 시작

pip install discovery-engine-api

API 키 받기:

# Step 1: request verification code (no password, no card)
curl -X POST https://disco.leap-labs.com/api/signup \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com"}'

# Step 2: submit code from email → get key
curl -X POST https://disco.leap-labs.com/api/signup/verify \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com", "code": "123456"}'
# → {"key": "disco_...", "credits": 10, "tier": "free_tier"}

또는 disco.leap-labs.com/developers에서 키를 생성하세요.

첫 번째 분석 실행:

from discovery import Engine

engine = Engine(api_key="disco_...")
result = await engine.discover(
    file="data.csv",
    target_column="outcome",
)

for pattern in result.patterns:
    if pattern.p_value < 0.05 and pattern.novelty_type == "novel":
        print(f"{pattern.description} (p={pattern.p_value:.4f})")

print(f"Explore: {result.report_url}")

실행에는 몇 분이 소요됩니다. discover()는 자동으로 폴링하며 진행 상황(대기열 위치, 예상 대기 시간, 현재 파이프라인 단계, 완료 예정 시간)을 기록합니다. 백그라운드 실행은 비동기 실행을 참조하세요.

→ 전체 Python SDK 참조 · 예제 노트북


결과 확인

result.patterns의 각 Pattern은 다음과 같이 보입니다(작물 수확량 데이터 세트의 실제 출력):

Pattern(
    description="When humidity is between 72–89% AND wind speed is below 12 km/h, "
                "crop yield increases by 34% above the dataset average",
    conditions=[
        {"type": "continuous", "feature": "humidity_pct",
         "min_value": 72.0, "max_value": 89.0},
        {"type": "continuous", "feature": "wind_speed_kmh",
         "min_value": 0.0, "max_value": 12.0},
    ],
    p_value=0.003,              # FDR-corrected
    novelty_type="novel",
    novelty_explanation="Published studies examine humidity and wind speed as independent "
                        "predictors, but this interaction effect — where low wind amplifies "
                        "the benefit of high humidity within a specific range — has not been "
                        "reported in the literature.",
    citations=[
        {"title": "Effects of relative humidity on cereal crop productivity",
         "authors": ["Zhang, L.", "Wang, H."], "year": "2021",
         "journal": "Journal of Agricultural Science"},
    ],
    target_change_direction="max",
    abs_target_change=0.34,     # 34% increase
    support_count=847,          # rows matching this pattern
    support_percentage=16.9,
)

주요 확인 사항:

  • 패턴은 조건의 조합입니다 — 단순히 "습도가 높을수록 좋다"가 아니라 습도 AND 풍속의 조합입니다.

  • 구체적인 임계값 — 모호한 상관관계가 아닌 72~89%와 같은 수치입니다.

  • 참신함 vs 확인적 — 모든 패턴은 분류됩니다. 확인적 패턴은 알려진 과학을 검증하고, 참신한 패턴은 여러분이 찾고자 했던 것입니다.

  • 인용문 — 무엇이 알려져 있는지 보여주어 무엇이 진정으로 새로운 것인지 확인할 수 있습니다.

  • **report_url**은 모든 패턴이 시각화된 대화형 웹 보고서로 연결됩니다.

result.summary는 LLM이 생성한 서술형 개요를 제공합니다:

result.summary.overview
# "Disco identified 14 statistically significant patterns. 5 are novel.
#  The strongest driver is a previously unreported interaction between humidity
#  and wind speed at specific thresholds."

result.summary.key_insights
# ["Humidity × low wind speed at 72–89% humidity produces a 34% yield increase — novel.",
#  "Soil nitrogen above 45 mg/kg shows diminishing returns when phosphorus is below 12 mg/kg.",
#  ...]

작동 원리

Disco는 데이터에 대한 프롬프트 엔지니어링이 아니라 파이프라인입니다. 다음과 같이 작동합니다:

  1. 데이터의 하위 집합에 대해 머신러닝 모델을 학습시킵니다.

  2. 해석 가능성 기술을 사용하여 학습된 패턴을 추출합니다.

  3. FDR 보정(Benjamini-Hochberg)을 통해 홀드아웃 데이터에서 모든 패턴을 검증합니다.

  4. 의미론적 검색을 통해 학술 문헌과 대조하여 살아남은 패턴을 확인합니다.

pandas 코드를 작성하거나 LLM에게 CSV를 보라고 요청하는 것으로는 이를 재현할 수 없습니다. 가설 기반 분석은 가설에서 시작하지 않기 때문에 놓치는 구조를 찾아냅니다.


데이터 준비

실행하기 전에 의미 없는 결과를 생성할 열을 제외하세요. Disco는 통계적으로 실제적인 패턴을 찾지만, 입력 데이터에 대상과 정의상 관련된 열이 포함되어 있으면 패턴은 동어반복이 됩니다.

제외할 항목:

  1. 식별자 — 행 ID, UUID, 환자 ID, 샘플 코드

  2. 데이터 누수 — 이름이 변경되거나 형식이 변경된 대상(예: 대상이 diagnosis_code일 때 diagnosis_text)

  3. 동어반복 열 — 대상과 동일한 구성의 대체 인코딩. 대상이 serious라면 serious_outcome, not_serious, death는 모두 같은 분류의 일부입니다. 대상이 profit이라면 revenue와 cost가 이를 구성합니다. 대상이 설문조사 지수라면 하위 항목은 동어반복입니다.

예시가 포함된 전체 지침: SKILL.md


매개변수

await engine.discover(
    file="data.csv",           # path, Path, or pd.DataFrame
    target_column="outcome",   # column to predict/explain
    analysis_depth=2,          # 2=default, higher=deeper analysis, lower = faster and cheaper
    visibility="public",       # "public" (always free, data and report is published) or "private" (costs credits)
    column_descriptions={      # improves pattern explanations and literature context
        "bmi": "Body mass index",
        "hdl": "HDL cholesterol in mg/dL",
    },
    excluded_columns=["id", "timestamp"],  # see "Preparing your data" above
    use_llms=False,                        # Defaults to False. If True, runs are slower and more expensive, but you get smarter pre-processing, summary page, literature context and novelty assessment. Public runs always use LLMs.
    title="My dataset",
    description="...", # improves pattern explanations and literature context
)

공개 실행은 무료이지만 결과는 게시됩니다. 비공개 데이터의 경우 visibility="private"로 설정하세요. 이는 크레딧이 차감됩니다.


비동기 실행

실행에는 몇 분이 소요됩니다. 에이전트 워크플로우나 병렬로 다른 작업을 수행하는 스크립트의 경우:

# Submit without waiting
run = await engine.run_async(file="data.csv", target_column="outcome", wait=False)
print(f"Submitted {run.run_id}, continuing...")

# ... do other things ...

result = await engine.wait_for_completion(run.run_id, timeout=1800)

동기식 스크립트 및 Jupyter 노트북의 경우:

result = engine.run(file="data.csv", target_column="outcome", wait=True)
# or: pip install discovery-engine-api[jupyter] for notebook compatibility

MCP 서버

Disco는 MCP 서버로 제공되므로 로컬 설치가 필요하지 않습니다.

{
  "mcpServers": {
    "discovery-engine": {
      "url": "https://disco.leap-labs.com/mcp",
      "env": { "DISCOVERY_API_KEY": "disco_..." }
    }
  }
}

도구: discovery_list_plans, discovery_estimate, discovery_upload, discovery_analyze, discovery_status, discovery_get_results, discovery_account, discovery_signup, discovery_signup_verify, discovery_login, discovery_login_verify, discovery_add_payment_method, discovery_subscribe, discovery_purchase_credits.

→ 전체 에이전트 스킬 파일


가격

비용

공개 실행

무료 — 결과 및 데이터가 게시됨

비공개 실행

파일 크기 및 구성에 따라 크레딧 차감 — engine.estimate() 사용

무료 티어

월 10 크레딧, 카드 불필요

연구자

월 $49 — 50 크레딧

팀

월 $199 — 200 크레딧

크레딧

크레딧당 $0.10

실행 전 견적 확인:

estimate = await engine.estimate(file_size_mb=10.5, num_columns=25, analysis_depth=2, visibility="private")
# estimate["cost"]["credits"] → 55
# estimate["account"]["sufficient"] → True/False

계정 관리는 완전히 프로그래밍 방식으로 이루어집니다. SDK 또는 REST API를 통해 결제 수단을 연결하고, 플랜을 구독하고, 크레딧을 구매하세요. Python SDK 참조 또는 SKILL.md를 참조하세요.


예상 데이터 형식

Disco는 플랫 테이블을 예상합니다(특성에 대한 열, 샘플에 대한 행).

| patient_id | age | bmi  | smoker | outcome |
|------------|-----|------|--------|---------|
| 001        | 52  | 28.3 | yes    | 1       |
| 002        | 34  | 22.1 | no     | 0       |
| ...        | ... | ...  | ...    | ...     |
  • 관측치당 한 행 — 환자, 샘플, 거래, 측정값 등

  • 특성당 한 열 — 숫자, 범주형, 날짜/시간 또는 자유 텍스트 모두 가능

  • 대상 열 하나 — 이해하고자 하는 결과. 최소 2개의 고유 값이 있어야 합니다.

  • 결측값은 괜찮음 — Disco가 자동으로 처리합니다. 미리 행을 삭제하거나 대치하지 마세요.

  • 피벗 불필요 — 데이터가 이미 플랫 테이블 형식이라면 바로 사용할 수 있습니다.

지원 형식: CSV, TSV, Excel (.xlsx), JSON, Parquet, ARFF, Feather. 최대 5GB.

지원되지 않음: 이미지, 원시 텍스트 문서, 중첩/계층적 JSON, 다중 시트 Excel(첫 번째 시트를 사용하거나 CSV로 내보내기)


다른 도구와의 비교

목표

도구

요약 통계, 데이터 품질

ydata-profiling, sweetviz

예측 모델

AutoML (auto-sklearn, TPOT, H2O)

빠른 상관관계

pandas, seaborn

데이터에 대한 특정 질문 답변

ChatGPT, Claude

무엇을 찾아야 할지 모르는 것을 찾기

Disco

Disco는 EDA나 AutoML을 대체하는 것이 아니라, 해당 도구들이 놓치는 패턴을 찾아냅니다. 우리는 알려진 진실 패턴이 있는 데이터 세트에서 18개의 데이터 분석 도구를 테스트했습니다. 대부분 잘못된 결과를 자신 있게 보고했지만, Disco는 모든 패턴을 찾아낸 유일한 도구였습니다.


링크


Available Tools

14 tools
discovery_accountA
Read-only
Inspect

Check your Disco account status.

Returns current plan, available credits (subscription + purchased), and
payment method status. Use this to verify you have sufficient credits
before running a private analysis.

Args:
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: api_key. Returns: result

discovery_add_payment_methodA
Idempotent
Inspect

Attach a Stripe payment method to your Disco account.

The payment method must be tokenized via Stripe's API first — card details
never touch Disco's servers. Required before purchasing credits
or subscribing to a paid plan.

To tokenize a card, call Stripe's API directly:
POST https://api.stripe.com/v1/payment_methods
with the stripe_publishable_key from your account info.

Args:
    payment_method_id: Stripe payment method ID (pm_...) from Stripe's API.
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: payment_method_id (required), api_key. Returns: result

discovery_analyzeA
Destructive
Inspect

Run Disco on tabular data to find novel, statistically validated patterns.

This is NOT another data analyst — it's a discovery pipeline that systematically
searches for feature interactions, subgroup effects, and conditional relationships
nobody thought to look for, then validates each on hold-out data with FDR-corrected
p-values and checks novelty against academic literature.

This is a long-running operation. Returns a run_id immediately.
Use discovery_status to poll and discovery_get_results to fetch completed results.

Use this when you need to go beyond answering questions about data and start
finding things nobody thought to ask. Do NOT use this for summary statistics,
visualization, or SQL queries.

Public runs are free but results are published. Private runs cost credits.
Call discovery_estimate first to check cost. Private report URLs require
sign-in — tell the user to sign in at the dashboard with the same email
address used to create the account (email code, no password needed).

Call discovery_upload first to upload your file, then pass the returned file_ref here.

Args:
    target_column: The column to analyze — what drives it, beyond what's obvious.
    file_ref: The file reference returned by discovery_upload.
    analysis_depth: Search depth (1=fast, higher=deeper). Default 1.
    visibility: "public" (free) or "private" (costs credits). Default "public".
    title: Optional title for the analysis.
    description: Optional description of the dataset.
    excluded_columns: Optional JSON array of column names to exclude from analysis.
    column_descriptions: Optional JSON object mapping column names to descriptions. Significantly improves pattern explanations — always provide if column names are non-obvious (e.g. {"col_7": "patient age", "feat_a": "blood pressure"}).
    author: Optional author name for the report.
    source_url: Optional source URL for the dataset.
    use_llms: Slower and more expensive, but you get smarter pre-processing, summary page, literature context and pattern novelty assessment. Only applies to private runs — public runs always use LLMs. Default false.
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: target_column (required), file_ref, analysis_depth, visibility, +8 more. Returns: result

discovery_estimateA
Read-only
Inspect

Estimate cost, time, and credit requirements before running an analysis.

Returns credit cost, estimated duration in seconds, whether you have
sufficient credits, and whether a free public alternative exists. Always call
this before discovery_analyze for private runs.

Args:
    file_size_mb: Size of the dataset in megabytes.
    num_columns: Number of columns in the dataset.
    num_rows: Number of rows (optional, improves time estimate).
    analysis_depth: Search depth (1=fast, higher=deeper). Default 1.
    visibility: "public" (free, results published) or "private" (costs credits).
    use_llms: Slower and more expensive, but you get smarter pre-processing, summary page, literature context and pattern novelty assessment. Only applies to private runs — public runs always use LLMs. Default false.
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: file_size_mb (required), num_columns (required), num_rows, analysis_depth, +3 more. Returns: result

discovery_get_resultsA
Read-only
Inspect

Fetch the full results of a completed Disco run.

Returns discovered patterns (with conditions, p-values, novelty scores,
citations), feature importance scores, a summary with key insights, column
statistics, and suggestions for what to explore next.

The response includes a `dashboard_urls` object with direct links to each
page of the interactive report — use these to direct the user to the most
relevant view:
- **summary**: AI-generated overview with key insights, novel findings, and plain-language explanation of the most important findings
- **patterns**: Full list of discovered patterns with conditions, effect sizes, p-values, novelty scores, citations, and interactive visualisations
- **features**: Feature importances, feature statistics and distribution plots, and correlation matrix
- **territory**: Interactive 3D map showing how patterns select different regions of the data

Only call this after discovery_status returns "completed".

Args:
    run_id: The run ID returned by discovery_analyze.
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: run_id (required), api_key. Returns: result

discovery_list_plansA
Read-only
Inspect

List available Disco plans with pricing.

No authentication required. Returns all available subscription tiers with credit allowances and pricing. Use this to help users choose a plan.

Inputs: no named parameters. Returns: result

discovery_loginA
Idempotent
Inspect

Get a new API key for an existing Disco account.

Sends a 6-digit verification code to the email address. Call
discovery_login_verify with the code to receive a new API key.
Use this when you need an API key for an account that already exists
(e.g. the key was lost or this is a new agent session).

Returns 404 if no account exists with this email — use discovery_signup instead.

Args:
    email: Email address of the existing account.

Inputs: email (required). Returns: result

discovery_login_verifyA
Idempotent
Inspect

Complete login and receive a new API key.

Call this after discovery_login returns {"status": "verification_required"}.
The user receives a 6-digit code by email — pass it here along with the
same email address. Returns a new API key on success.

Args:
    email: Email address used in the discovery_login call.
    code: 6-digit verification code from the email.

Inputs: email (required), code (required). Returns: result

discovery_purchase_creditsA
Destructive
Inspect

Purchase Disco credit packs using a stored payment method.

Credits cost $0.10 each, sold in packs of 100 ($10/pack). Credits are used
for private analyses (public analyses are free). Requires a payment method
on file — use discovery_add_payment_method first.

Args:
    packs: Number of 100-credit packs to purchase. Default 1.
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: packs, api_key. Returns: result

discovery_signupA
Idempotent
Inspect

Create a Disco account and get an API key.

Provide an email address to start the signup flow. If email verification
is required, returns {"status": "verification_required"} — the user will
receive a 6-digit code by email, then call discovery_signup_verify to
complete signup and receive the API key. The free tier (10 credits/month,
unlimited public runs) is active immediately. No authentication required.

Returns 409 if the email is already registered.

Args:
    email: Email address for the new account.
    name: Display name (optional — defaults to email local part).

Inputs: email (required), name. Returns: result

discovery_signup_verifyA
Idempotent
Inspect

Complete Disco signup using an email verification code.

Call this after discovery_signup returns {"status": "verification_required"}.
The user receives a 6-digit code by email — pass it here along with the
same email address used in discovery_signup. Returns an API key on success.

Args:
    email: Email address used in the discovery_signup call.
    code: 6-digit verification code from the email.

Inputs: email (required), code (required). Returns: result

discovery_statusA
Read-only
Inspect

Check the status of a Disco run.

Returns current status and progress details:
- status: "pending" | "processing" | "completed" | "failed"
- job_status: underlying job queue status
- queue_position: position in queue when pending (1 = next up)
- current_step: active pipeline step (preprocessing, training, interpreting, reporting)
- estimated_seconds: estimated total processing time in seconds
- estimated_wait_seconds: estimated queue wait time in seconds (pending only)

Poll this after calling discovery_analyze — runs typically take 3–15 minutes.
Use discovery_get_results to fetch full results once status is "completed".

Args:
    run_id: The run ID returned by discovery_analyze.
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: run_id (required), api_key. Returns: result

discovery_subscribeA
DestructiveIdempotent
Inspect

Subscribe to or change your Disco plan.

Available plans:
- "free_tier": Explorer — free, 10 credits/month
- "tier_1": Researcher — $49/month, 50 credits/month
- "tier_2": Team — $199/month, 200 credits/month

Paid plans require a payment method on file. Credits roll over on paid plans.

Args:
    plan: Plan tier ID ("free_tier", "tier_1", or "tier_2").
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: plan (required), api_key. Returns: result

discovery_uploadAInspect

Upload a dataset file and return a file reference for use with discovery_analyze.

Call this before discovery_analyze. Pass the returned result directly to
discovery_analyze as the file_ref argument.

Provide exactly one of: file_url, file_path, or file_content.

Args:
    file_url: A publicly accessible http/https URL. The server downloads it directly.
              Best option for remote datasets.
    file_path: Absolute path to a local file. Only works when running the MCP server
               locally (not the hosted version). Streams the file directly — no size limit.
    file_content: File contents, base64-encoded. For small files when a URL or path
                  isn't available. Limited by the model's context window.
    file_name: Filename with extension (e.g. "data.csv"), for format detection.
               Only used with file_content. Default: "data.csv".
    api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set.

Inputs: file_content, file_name, file_path, file_url, +1 more. Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.7/5.0

    Scored across 14 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap. Account management (discovery_account, discovery_add_payment_method), authentication (discovery_login, discovery_login_verify, discovery_signup, discovery_signup_verify), analysis workflow (discovery_upload, discovery_estimate, discovery_analyze, discovery_status, discovery_get_results), and billing (discovery_list_plans, discovery_purchase_credits, discovery_subscribe) are all cleanly separated. An agent can easily distinguish between tools like discovery_analyze (run analysis) and discovery_estimate (check cost/time) despite both relating to analysis preparation.

    Naming Consistency5/5

    All 14 tools follow a perfect 'discovery_verb_noun' pattern with consistent snake_case throughout. The naming convention is highly predictable: discovery_account, discovery_analyze, discovery_estimate, discovery_get_results, discovery_list_plans, etc. This consistency makes the tool set immediately understandable and navigable.

    Tool Count5/5

    14 tools is ideal for this server's comprehensive scope covering authentication, data upload, analysis execution, results retrieval, and billing management. Each tool serves a specific, necessary function in the end-to-end workflow. The count is neither too thin (missing critical operations) nor bloated (no redundant tools), perfectly matching the domain of a sophisticated data analysis platform.

    Completeness5/5

    The tool surface provides complete coverage for the Disco platform's domain. It includes full authentication flow (signup/login with verification), account management, billing operations (plans, payments, credits), data upload, analysis estimation, execution, status monitoring, and results retrieval. There are no dead ends or gaps—every logical step in the workflow has a corresponding tool, creating a coherent end-to-end experience.

    Maintenance

    ActivitySlowing
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers