LakeXpress MCP Server
A Model Context Protocol (MCP) server for LakeXpress — a database to Parquet export tool with sync management and data lake publishing.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx lakexpress-mcp==0.1.6Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
LAKEXPRESS_PATH=<value> LAKEXPRESS_TIMEOUT=<value> LAKEXPRESS_LOG_DIR=<value> FASTBCP_DIR_PATH=<value> LOG_LEVEL=<value> claude mcp add io.github.arpe-io-lakexpress-mcp -- uvx lakexpress-mcp==0.1.6在終端機中執行。
{ "mcpServers": { "io.github.arpe-io-lakexpress-mcp": { "command": "uvx", "args": [ "lakexpress-mcp==0.1.6" ], "env": { "LAKEXPRESS_PATH": "<value>", "LAKEXPRESS_TIMEOUT": "<value>", "LAKEXPRESS_LOG_DIR": "<value>", "FASTBCP_DIR_PATH": "<value>", "LOG_LEVEL": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
A Model Context Protocol (MCP) server for LakeXpress — a database to Parquet export tool with sync management and data lake publishing.
MCP server for LakeXpress — automated database-to-cloud data pipeline as Parquet
pip install -e ".[dev]"
Add to your Claude Code MCP settings:
{
"mcpServers": {
"lakexpress": {
"command": "python",
"args": ["-m", "src.server"],
"cwd": "/path/to/lakexpress-mcp",
"env": {
"LAKEXPRESS_PATH": "/path/to/LakeXpress",
"LAKEXPRESS_TIMEOUT": "3600",
"LAKEXPRESS_LOG_DIR": "./logs",
"FASTBCP_DIR_PATH": "/path/to/FastBCP/"
}
}
}
}
Or using the installed entry point:
{
"mcpServers": {
"lakexpress": {
"command": "lakexpress-mcp",
"env": {
"LAKEXPRESS_PATH": "/path/to/LakeXpress",
"FASTBCP_DIR_PATH": "/path/to/FastBCP/"
}
}
}
}
preview_commandBuild and preview any LakeXpress CLI command without executing it. Supports all 14 subcommands with full parameter validation.
execute_commandExecute a previously previewed command. Requires confirmation: true as a safety mechanism.
validate_auth_fileValidate that an authentication file exists, is valid JSON, and optionally check for specific auth_id entries.
list_capabilitiesList all supported source databases, log databases, storage backends, publishing targets, compression types, and available commands.
suggest_workflowGiven a use case (source DB type, storage destination, optional publish target), suggest the full sequence of LakeXpress commands with example parameters.
get_versionReport the detected LakeXpress binary version and capabilities.
# 1. Initialize the log database (first-time setup)
LakeXpress logdb init -a auth.json --log_db_auth_id export_db
# 2. Create a sync configuration
LakeXpress config create -a auth.json --log_db_auth_id export_db \
--source_db_auth_id prod_db --source_schema_name sales \
--output_dir ./exports --compression_type Zstd
# 3. Execute the sync
LakeXpress sync --sync_id <sync_id>
# 4. Check status
LakeXpress status -a auth.json --log_db_auth_id export_db --sync_id <sync_id>
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
python -m pytest tests/ -v
# Run with coverage
python -m pytest tests/ -v --cov=src --cov-report=term-missing
MIT
MCP server for LakeXpress — automated database-to-cloud data pipeline as Parquet
{ "mcpServers": { "io.github.arpe-io-lakexpress-mcp": { "command": "uvx", "args": [ "lakexpress-mcp==0.1.6" ], "env": { "LAKEXPRESS_PATH": "<value>", "LAKEXPRESS_TIMEOUT": "<value>", "LAKEXPRESS_LOG_DIR": "<value>", "FASTBCP_DIR_PATH": "<value>", "LOG_LEVEL": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:LAKEXPRESS_PATH, LAKEXPRESS_TIMEOUT, LAKEXPRESS_LOG_DIR, FASTBCP_DIR_PATH, LOG_LEVEL。
Lakexpress 透過 stdio 在本機執行。
上次檢查時間:2026-11-09。 MCP server for LakeXpress — automated database-to-cloud data pipeline as Parquet