data-engineering-mcp
Local MCP server for exploring XLSX-derived schemas and generating Oracle SELECT/WITH SQL without database access.
List, describe, and search cataloged tables and columns.
Infer candidate relationships and find MEDIUM/HIGH-confidence paths between tables.
Refresh the catalog and report catalog statistics/status.
Generate parameterized Oracle SELECT/WITH SQL, simple SELECT statements, and candidate JOINs.
Explain SELECT/WITH SQL conservatively.
It does not execute SQL, access databases, or modify XLSX files.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@data-engineering-mcp Generate Oracle SQL to join the user and person tables for active users"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
data-engineering-mcp
Generic, local, and offline MCP server that transforms XLSX file headers into a searchable catalog, infers candidate relationships, and generates only Oracle SQL SELECT/WITH. It does not access databases, does not execute SQL, and has no Power BI integration or dependency.
Requirements and installation
Python 3.12
MCP Python SDK 2.x (
MCPServer, the current public API of the installed version)
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -e ".[dev]"Runtime dependencies: mcp, pandas, openpyxl, and pydantic; tests use pytest. The catalog uses openpyxl directly to open the workbooks in read-only mode and reads only the first required row.
Related MCP server: DataPilot MCP Server
Data and architecture
Datasets are provided locally by the user and are not part of the repository. Place .xlsx files in data/; they remain available to the MCP but are ignored by Git. Each file is a table. The logical name strips .xlsx, the rawzn. prefix, and the _SINTETICO suffix, using a case-insensitive comparison. The first sheet not named SQL that has headers is used; records do not participate in discovery.
data/*.xlsx -> Catalog -> RelationshipEngine -> SQLGenerator
\-> explicação conservadora de SQLNew files are discovered by atualizar_catalogo, with no code changes. The update also detects removals and changes in the ordered header list, updates the timestamp, and recalculates candidates. The local schemas/datasets directory is configurable via the DATA_ENGINEERING_MCP_DATA_DIR variable; the default is data/.
Execution and testing
.\.venv\Scripts\data-engineering-mcp.exe
# ou
.\.venv\Scripts\python.exe -m data_engineering_mcp.server
.\.venv\Scripts\python.exe -m pytest
.\.venv\Scripts\python.exe scripts\smoke_test.pyThe default transport is stdio. Logs go to stderr to avoid corrupting the protocol. Set DATA_ENGINEERING_MCP_DATA_DIR to use a different local folder.
Tools
listar_tabelas,descrever_tabela,buscar_coluna,buscar_tabelasinferir_relacionamentos,encontrar_caminho,gerar_joinatualizar_catalogo,status_catalogogerar_sql,gerar_select,explicar_sql
gerar_sql receives tabelas, colunas, and typed filters {table?, column, operator, value}. Operators: =, <>, >, >=, <, <=, IN, IS NULL, IS NOT NULL, LIKE. Values become bind variables (:p1), never concatenated text. Ambiguous columns require TABELA.COLUNA. The default JOIN is LEFT JOIN, a conservative choice that preserves rows from the first table; the tool reports MEDIUM candidates and rejects LOW by default.
Example arguments:
{
"tabelas": ["RAW_HAP_TB_USUARIO", "RAW_HAP_TB_PESSOA"],
"colunas": ["CD_USUARIO", "NM_PESSOA_RAZAO_SOCIAL"],
"filtros": [{"column": "FL_STATUS_USUARIO", "operator": "=", "value": 2}]
}Relationship confidence
Every result is a nominal candidate, never a confirmed PK/FK. The score starts at 20 for identical column names; adds 30 for CD_, ID_, or NU_ prefixes; adds 20 when the column entity appears in a table name, plus 10 more if it appears in both. Occurrence in more than two tables subtracts 5 per extra occurrence (maximum 25); generic columns without an identifier prefix subtract 25. HIGH >= 75, MEDIUM >= 50, LOW < 50. No data values are read and no cardinality is computed, and this version has no explicit PK/FK metadata.
Security and limitations
Only structured Oracle SELECT/WITH SQL is generated. There is no surface for DDL/DML, arbitrary filter SQL, credentials, network, database, or external APIs.
Known limitations:
relationships are inferred nominally and may produce false positives or semantic negatives;
this version has no explicit PK/FK metadata;
generic or shared columns may lead to inappropriate paths;
LOWcandidates must not be used automatically;MEDIUMcandidates are inferences, not confirmations;explicar_sqlperforms conservative syntactic analysis and does not semantically validate the query against Oracle;some accent-containing logs may display incorrectly on a Windows console configured as CP1252.
XLSX files are always treated as read-only. Local datasets (data/*, *.xlsx, *.xls, *.csv, and *.parquet) are ignored and are not part of the repository.
Available Tools
12 toolsatualizar_catalogoA
Revarre XLSX, detecta mudanças de schema e recalcula relacionamentos.
Inputs: no named parameters.
buscar_colunaA
Busca uma coluna exata, sem diferenciar maiúsculas/minúsculas.
Inputs: coluna (required). Returns: result
buscar_tabelasA
Busca parcial case-insensitive no nome das tabelas.
Inputs: termo (required). Returns: result
descrever_tabelaC
Descreve arquivo, aba e cabeçalhos de uma tabela.
Inputs: tabela (required).
encontrar_caminhoC
Encontra os melhores caminhos de relacionamentos candidatos com confiança MEDIUM ou HIGH.
Inputs: tabela_origem (required), tabela_destino (required). Returns: result
explicar_sqlA
Explica conservadoramente uma consulta SELECT/WITH sem executá-la.
Inputs: sql (required).
gerar_joinB
Propõe JOIN candidato direto entre duas tabelas, sem afirmar chave estrangeira.
Inputs: tabela_origem (required), tabela_destino (required).
gerar_selectB
Gera SELECT Oracle simples de uma tabela, sem executar SQL.
Inputs: tabela (required), colunas.
gerar_sqlC
Gera SELECT Oracle estrutural, parametrizado e sem executar SQL.
Inputs: tabelas (required), colunas, filtros, permitir_baixa_confianca.
inferir_relacionamentosA
Retorna relacionamentos candidatos inferidos somente por metadados.
Inputs: no named parameters. Returns: result
listar_tabelasB
Lista deterministicamente as tabelas lógicas do catálogo local.
Inputs: no named parameters. Returns: result
status_catalogoA
Informa estatísticas e timestamp do catálogo.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools target clearly distinct actions: catalog listing, table description, schema search, relationship inference, path finding, and SQL generation. The only mild overlap is between gerar_sql and gerar_select, both generating SELECT statements, though their descriptions differentiate structural vs. simple generation.
Tool names consistently use snake_case Portuguese with a mostly verb-first pattern like listar_tabelas, buscar_coluna, and gerar_join. The exception is status_catalogo, which uses a noun instead of a verb, but the overall pattern remains predictable.
Twelve tools is well-scoped for a data engineering catalog server covering metadata browsing, search, relationship inference, and SQL generation. Each tool serves a meaningful purpose without redundancy or bloat.
The tool set covers the apparent domain comprehensively: listing, describing, updating, searching, relationship inference, path discovery, status reporting, and SQL generation/explanation. No obvious dead ends exist for the catalog-focused purpose.
Related MCP Connectors
Excel analytics: inspect, query (JSON rows), charts, and JSON-to-xlsx workbook writing.
Read-only MCP over your Excel or Airtable plus the PDFs beside it, joined as one relational dataset.
SQL validation, formatting, parsing, metadata extraction, linting, and security analysis.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables extraction and querying of database schema metadata from PostgreSQL, Snowflake, SQL Server, BigQuery, and Oracle databases, saving results locally for analysis.37 PyPIMIT
- FlicenseNot gradedqualityDmaintenanceProvides tools to inspect dataset schema, profile, preview, and execute read-only SQL queries on uploaded CSV/Excel files.-
- AlicenseNot gradedqualityDmaintenanceLocal MCP server that connects Claude to real Excel .xlsx files for financial and operational analysis. Enables reading, comparing, cleaning, reconciling, and writing to Excel files without cloud dependency.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables offline analysis of MySQL slow query logs, individual SQL statements, and MyBatis mappers to produce deterministic index recommendations and migration SQL without requiring an API key.1MIT