pip install misata

pip install "misata[llm]"        # multi-provider LLM schema generation
pip install "misata[documents]"  # PDF output via weasyprint
pip install "misata[advanced]"   # SDV/CTGAN statistical synthesis
pip install "misata[mcp]"        # MCP server — expose Misata to Claude, Cursor, and other AI agents

pip install "misata[mcp]"

{
  "mcpServers": {
    "misata": {
      "command": "misata-mcp"
    }
  }
}

misata generate \
  --story "Brazilian fintech with R$ payments, CPF verification, and 3% fraud" \
  --rows 1000 \
  --output-dir ./demo_data

# Writes CSVs plus:
# ./demo_data/oracle_report.json

import misata

# One sentence → multi-table DataFrame dict
tables = misata.generate("A SaaS company with 5k users, monthly subscriptions, and 20% churn")

print(tables["users"].head())
print(tables["subscriptions"].head())

# Or from the CLI
misata generate --story "A SaaS company with 5k users and 20% churn" --rows 5000

import misata

schema = misata.parse("Brazilian fintech with CPF verification", rows=1000)
tables = misata.generate_from_schema(schema)
oracle = misata.build_oracle_report(tables, schema, seed=schema.seed)

print(oracle["passed"])
print(oracle["advisory"]["locale_domain_fit"]["locale"])

tables = misata.generate("A fintech startup with 10k customers, fraud rate 3%, and IBAN accounts")

misata init           # scaffolds misata.yaml in the current directory
misata generate       # reads misata.yaml automatically

# misata.yaml
name: my-app
seed: 42

tables:
  users:
    rows: 1000
    columns:
      user_id: { type: int, unique: true }
      email:   { type: text, text_type: email }
      plan:    { type: categorical, choices: [free, pro, enterprise] }

  orders:
    rows: 5000
    columns:
      order_id: { type: int, unique: true }
      user_id:  { type: foreign_key }
      amount:   { type: float, min: 5.0, max: 500.0 }

relationships:
  - "users.user_id → orders.user_id"

constraints:
  - name: amount_above_cost
    table: orders
    type: inequality
    column_a: amount
    operator: ">"
    column_b: cost

schema = misata.load_yaml_schema("misata.yaml")
tables = misata.generate_from_schema(schema)

from misata import schema_from_db, generate_from_schema, seed_database

# Introspect the live schema — no manual column definitions
schema = schema_from_db("postgresql://user:pass@localhost/myapp")
tables = generate_from_schema(schema)

# Seed it back — insert order respects FK dependencies automatically
report = seed_database(tables, "postgresql://user:pass@localhost/myapp_dev")
# SeedReport: seeded 6 tables, 47,300 rows in 1.2s

# One-command workflow
misata init --db postgresql://user:pass@localhost/myapp   # writes misata.yaml
misata generate --db-url postgresql://user:pass@localhost/myapp_dev --db-create

from misata import seed_from_sqlalchemy_models
from myapp.models import Base

report = seed_from_sqlalchemy_models(Base, db_url="sqlite:///test.db", row_count=500, create_tables=True)

schema = misata.from_dict_schema({
    "customers": {
        "id":    {"type": "integer", "primary_key": True},
        "email": {"type": "email"},
        "plan":  {"type": "string", "enum": ["free", "pro", "enterprise"]},
    },
    "orders": {
        "id":          {"type": "integer", "primary_key": True},
        "customer_id": {"type": "integer", "foreign_key": {"table": "customers", "column": "id"}},
        "amount":      {"type": "float", "min": 1.0, "max": 999.0},
    },
}, row_count=5_000)

tables = misata.generate_from_schema(schema)

from misata import LLMSchemaGenerator

gen = LLMSchemaGenerator(provider="groq")          # free tier, fast
# gen = LLMSchemaGenerator(provider="anthropic")   # Claude
# gen = LLMSchemaGenerator(provider="ollama", model="llama3")  # fully local, no API key

schema = gen.generate_from_story(
    "A fraud detection dataset — 2% positive rate, FICO scores, transaction velocity features"
)
tables = misata.generate_from_schema(schema)

tables = misata.generate("A fintech company with 1000 customers", seed=1)

# Add 1 000 more rows — IDs auto-offset, FK integrity maintained across both batches
tables = misata.generate_more(tables, schema, n=1000, seed=2)
print(len(tables["customers"]))  # 2000

# Locale is detected automatically — no extra flag needed
tables = misata.generate("German SaaS company in Berlin with 2k enterprise customers")
# → names from de_DE Faker pool, salary ~ lognormal(μ=10.71, σ=0.5) ≈ €45k median,
#   postcodes are 5-digit, company names end in GmbH/AG/UG

tables = misata.generate("Brazilian fintech with R$ payments and CPF verification, 50k users")
# → pt_BR names, salary median ~BRL 33.6k, national IDs match CPF format ###.###.###-##

tables = misata.generate("Indian startup in Bangalore with ₹ salary bands and Aadhaar KYC")
# → hi_IN names, salary median ~₹350k/yr, national IDs match Aadhaar 12-digit format

schema = misata.parse("An ecommerce store with 10k orders")
tables = misata.generate_from_schema(schema)  # defaults to en_US

# CLI
misata generate --story "Ecommerce store" --locale ja_JP

# Inspect a locale pack directly
pack = misata.get_locale_pack("de_DE")
print(pack.salary_median)       # 45000
print(pack.currency_symbol)     # €
print(pack.top_cities[:3])      # ['Berlin', 'Hamburg', 'Munich']
print(pack.company_suffixes)    # ['GmbH', 'AG', 'UG', 'KG', 'e.K.']

# Auto-detect from a story
locale = misata.detect_locale("South Korean company in Seoul with KRW salaries")
# → "ko_KR"

from misata.constraints import (
    InequalityConstraint,   # price > cost on every row
    ColumnRangeConstraint,  # min_price <= price <= max_price
    RatioConstraint,        # 70% free / 30% pro
    UniqueConstraint,       # no duplicate (user_id, date) pairs
    SumConstraint,          # total_hours per employee per day <= 8
    NotNullConstraint,      # no nulls in required columns
)

c = InequalityConstraint("price", ">", "cost")
df = c.apply(df)

misata.to_parquet(tables, "data/")
misata.to_duckdb(tables, "data/dataset.duckdb")
misata.to_jsonl(tables, "data/")

# Built-in templates: invoice, patient_report, transaction_receipt, user_profile
paths = misata.generate_documents(
    tables, "invoice", table="orders", output_dir="/tmp/invoices", format="html"
)
# format="pdf" requires: pip install "misata[documents]"

# Custom Jinja2 template
tmpl = "<h1>Order #{{ order_id }}</h1><p>Amount: ${{ amount }}</p>"
paths = misata.generate_documents(tables, tmpl, table="orders", output_dir="/tmp/custom")

bundle = misata.analyze_generation(tables, schema)

print(bundle.data_card.summary())        # row counts, null rates, type distribution
print(bundle.fidelity_report.score)      # 0–1 statistical fidelity score vs. schema intent
print(bundle.privacy_report.pii_risk)    # column-level PII exposure analysis

story / YAML / dict / DB introspection / MCP tool call
              ↓
        StoryParser  ·  locale detection  ·  load_yaml_schema  ·  schema_from_db
              ↓
        DetectionReport  (domain, confidence, near_misses, table_preview, warnings)
              ↓
        SchemaConfig  ←  validate_schema() catches issues before any rows are generated
              ↓
        DataSimulator
          ├─ topological sort (FK dependency order)
          ├─ domain priors  →  locale priors (salary, age, monetary)
          ├─ constraint engine (inequality, range, ratio, sum, unique)
          ├─ outcome curves (monthly targets from narrative control points)
          ├─ Iman-Conover correlation engine (Cholesky, preserves marginals)
          └─ RealisticTextGenerator (Faker locale + Kaggle vocabulary assets)
              ↓
        {table_name: DataFrame}
              ↓
        seed_database  ·  to_parquet  ·  to_duckdb  ·  generate_documents  ·  MCP CSV output

# All of these produce precise, shaped outcome curves:
misata.generate("SaaS mrr from $50k in Jan to $200k in Dec, with a Q3 slump")
misata.generate("Ecommerce orders, Black Friday spike, Christmas peak")
misata.generate("SaaS startup — MRR 10x growth over the year")
misata.generate("Fintech payments — strong Q4, dip in Q1")

git clone https://github.com/rasinmuhammed/misata
cd misata
pip install -e ".[dev]"
pytest tests/