Avanti Fellows PostgreSQL MCP Server

Instructions

Useful for understanding what data looks like without
writing a full query.

Args:
    table_name: Name of the table
    schema_name: Schema name (default: public)
    limit: Number of rows to return (default: 10, max: 100)

Returns:
    JSON array of sample rows

Implementation Reference

• mcp_postgres/server.py:174-202 (handler)

  The handler function for the 'sample_data' MCP tool. It is decorated with @mcp.tool() for registration and implements fetching up to 100 sample rows from a PostgreSQL table, serializing them to JSON.

  @mcp.tool()
  async def sample_data(table_name: str, schema_name: str = "public", limit: int = 10) -> str:
      """Get sample rows from a table.
  
      Useful for understanding what data looks like without
      writing a full query.
  
      Args:
          table_name: Name of the table
          schema_name: Schema name (default: public)
          limit: Number of rows to return (default: 10, max: 100)
  
      Returns:
          JSON array of sample rows
      """
      limit = min(limit, 100)  # Cap at 100 rows
  
      # Use identifier quoting to prevent SQL injection
      sql = f'SELECT * FROM "{schema_name}"."{table_name}" LIMIT {limit}'
  
      try:
          async with get_connection() as conn:
              rows = await conn.fetch(sql)
              results = []
              for row in rows:
                  results.append({k: _serialize_value(v) for k, v in dict(row).items()})
              return json.dumps(results, indent=2, default=str)
      except Exception as e:
          return json.dumps({"error": str(e)})