cd data-manage
pip install -e .

# 1. point datamgr at a central warehouse (created if missing)
dm init-root D:/datasets

# 2a. import a raw data folder -- harvests variable names + labels from a .dta,
#     copies the file into a new clean-id folder under the warehouse
dm import "原始数据包" --id csmar_annual --name "CSMAR 上市公司年度财务"

# 2b. (or) scaffold an empty dataset and fill the manifest by hand
dm init csmar_annual --name "CSMAR 上市公司年度财务"

# 3. rebuild the index
dm refresh

# 4. discover
dm list                          # all datasets, one line each
dm show csmar_annual             # full manifest, rendered
dm search 资产负债率               # fuzzy-search across all variables/labels
dm variables --role control      # list all control variables available
dm variables --label 占比          # filter variables by label
dm stats csmar_annual --refresh  # compute rows/cols/n_firms, cache to manifest
dm verify                        # validate manifests + check file paths exist

# 5. pull data into an analysis working directory (backup + provenance)
dm export csmar_annual control_vars --to D:/my_paper
#   -> D:/my_paper/data/*.dta        (copied files, ready for `use "data/xxx.dta"`)
#   -> D:/my_paper/data_sources.txt  (where each file came from, for traceability)

src/datamgr/
  config.py        warehouse root resolution
  core/
    manifest.py    schema + load/validate/save
    registry.py    scan -> _registry.json index
    search.py      fuzzy search over the index (rapidfuzz)
    stats.py       compute rows/cols/n_firms from a .dta/.csv (explicit --refresh only)
    importing.py   harvest variables from a .dta/.csv -> manifest scaffold
    exporting.py   copy data files to a working dir + provenance txt
  cli/main.py      `dm` command
  mcp/server.py    read-only MCP server for AI discovery (stdio)

# direct
python -m datamgr.mcp.server
# or via entry point
datamgr-mcp

{
  "mcp": {
    "servers": {
      "datamgr": {
        "command": "python",
        "args": ["-m", "datamgr.mcp.server"],
        "env": { "DATAMGR_ROOT": "D:/datasets" }
      }
    }
  }
}