数据库模式搜索服务

data/
├── index/
│   └── index.db              # SQLite index with FTS5 + vector search
└── map/
    ├── postgres_production/
    │   └── domains/
    │       ├── authentication/
    │       │   └── tables/
    │       │       ├── auth.users.json
    │       │       ├── auth.users.md
    │       │       ├── auth.sessions.json
    │       │       └── ...
    │       ├── payments/
    │       │   └── tables/
    │       │       ├── public.payments.json
    │       │       ├── public.merchants.json
    │       │       └── ...
    │       ├── realtime/
    │       ├── security/
    │       └── storage/
    └── snowflake_production/
        └── domains/
            ├── payments/
            │   └── tables/
            │       └── PUBLIC.DABSTEP_PAYMENTS.json
            └── workflow/
                └── tables/
                    ├── PUBLIC.DABSTEP_TASKS.json
                    ├── PUBLIC.DABSTEP_SUBMISSIONS.json
                    └── PUBLIC.DABSTEP_TASK_SCORES.json

{
  "table": "payments",
  "schema": "public",
  "database": "postgres_production",
  "description": "Payment transactions processed through the system...",
  "row_count": 138236,
  "columns": [
    {
      "name": "payment_id",
      "type": "character varying",
      "nullable": false,
      "description": "Unique identifier for each payment transaction..."
    }
  ],
  "primary_key": ["payment_id"],
  "foreign_keys": [],
  "indexes": [
    {
      "index_name": "payments_pkey",
      "columns": ["payment_id"],
      "is_unique": true
    }
  ]
}

CREATE VIRTUAL TABLE documents_fts USING fts5(
    content, summary, keywords,
    content='documents', content_rowid='id'
);

CREATE VIRTUAL TABLE documents_vec USING vec0(
    document_id INTEGER PRIMARY KEY,
    embedding float[1536]  -- OpenAI text-embedding-3-small
);

pip install -r requirements.txt

OPENAI_API_KEY=sk-your-api-key-here

python setup_db.py

python server.py

docker build -t db-context-mcp .
docker run -p 8000:8000 --env-file .env db-context-mcp

python client.py

# 1. Copy environment template
cp .env.example .env

# 2. Edit .env with your configuration
#    - Set a secure SFTP_PASSWORD
#    - Add OPENAI_API_KEY for vector search

# 3. Start all services
docker-compose up -d

# Connect via SFTP
sftp -P 2222 datauser@localhost

# Default credentials (change in .env):
# User: datauser
# Password: changeme

# Start all services
docker-compose up -d

# View logs
docker-compose logs -f

# Stop all services
docker-compose down

# Rebuild after changes
docker-compose up -d --build

# View service status
docker-compose ps

list_databases()

{
  "databases": [
    {"name": "postgres_production", "table_count": 37, "domains": [...], "schemas": [...]},
    {"name": "snowflake_production", "table_count": 4, "domains": [...], "schemas": [...]}
  ]
}

list_domains(
    database: str = ""    # Optional: filter by database
)

list_tables(
    database: str = "",   # Optional: filter by database
    domain: str = ""      # Optional: filter by domain
)

search_fts(
    query: str,           # Search text (supports AND, OR, NOT, "exact phrase")
    database: str = "",   # Optional: filter by database
    domain: str = "",     # Optional: filter by domain
    doc_type: str = "",   # Optional: filter by type ("table" or "column")
    limit: int = 10       # Max results (1-50)
)

search_vector(
    query: str,           # Natural language query
    database: str = "",   # Optional: filter by database
    domain: str = "",     # Optional: filter by domain
    doc_type: str = "",   # Optional: filter by type
    limit: int = 10       # Max results (1-50)
)

search_db_map(
    query: str,           # Free-text search string
    top_k: int = 3        # Number of results
)

search_tables(
    query: str,           # Search text
    database: str = "",   # Optional: filter by database
    domain: str = "",     # Optional: filter by domain
    limit: int = 5        # Max results (1-20)
)

list_columns(
    table: str,           # Table name (e.g., "merchants", "DABSTEP_PAYMENTS")
    database: str = ""    # Optional: filter by database
)

get_table_schema(
    table: str,                    # Table name
    database: str = "",            # Optional: filter by database
    include_samples: bool = False  # Include sample values if available
)

get_domain_overview(
    domain: str,          # Domain name (e.g., "payments", "authentication")
    database: str = ""    # Optional: filter by database
)

get_join_path(
    source_table: str,    # Starting table
    target_table: str,    # Target table
    database: str = "",   # Optional: filter by database
    max_hops: int = 3     # Maximum join hops
)

get_common_relationships(
    database: str = "",   # Optional: filter by database
    domain: str = "",     # Optional: filter by domain
    limit: int = 10       # Max relationships
)

# List all databases
list_databases()
# → postgres_production (37 tables), snowflake_production (4 tables)

# List tables in a specific database
list_tables(database="snowflake_production")

# List business domains
list_domains()

# FTS5 search
search_fts(query="payment fraud", limit=5)

# Semantic search
search_vector(query="tables related to financial transactions", limit=3)

# Search within a specific database
search_fts(query="merchant", database="postgres_production")

# Get schema for a table (auto-detects database)
get_table_schema(table="payments")

# Get schema from specific database
get_table_schema(table="payments", database="postgres_production")
get_table_schema(table="DABSTEP_PAYMENTS", database="snowflake_production")

# Get columns only
list_columns(table="merchants", database="postgres_production")

# Find join path between tables
get_join_path(
    source_table="merchants",
    target_table="payments",
    database="postgres_production"
)

# Get common relationships in a domain
get_common_relationships(domain="payments")

┌─────────────────────────────────────────────────────────────┐
│                     MCP Client                              │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│                   FastMCP Server                            │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────────────┐ │
│  │ search_fts  │  │search_vector│  │ Schema Tools        │ │
│  └──────┬──────┘  └──────┬──────┘  └──────────┬──────────┘ │
│         │                │                     │            │
│         ▼                ▼                     ▼            │
│  ┌─────────────────────────────┐    ┌─────────────────────┐│
│  │   data/index/index.db      │    │   data/map/*.json   ││
│  │  ┌───────────┐ ┌─────────┐ │    │   (source schemas)  ││
│  │  │   FTS5    │ │ Vectors │ │    └─────────────────────┘│
│  │  └───────────┘ └─────────┘ │                            │
│  └─────────────────────────────┘                            │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼ (vector search only)
                   ┌────────────────┐
                   │  OpenAI API    │
                   │  (embeddings)  │
                   └────────────────┘